commit c35130be7654b595dbf8a1cfc5090e79cb553f31
parent 5fdfb44dee79ae049634182e66638143e9c30d37
Author: Brian Graham <brian@buildingbetterteams.de>
Date: Tue, 7 Apr 2026 17:28:03 +0200
PCA analysis page, remove violin dots
- PCA: Python script computes 3-component PCA on one-hot encoded axes.
Dashboard page with 2D projection scatter, loadings table, variance
explained. PC1=14.6%, PC2=12.7%, PC3=5.8%.
- Violin: removed scatter dots, boxes only.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat:
5 files changed, 4008 insertions(+), 13 deletions(-)
diff --git a/dashboard/src/components/PCAPlot.tsx b/dashboard/src/components/PCAPlot.tsx
@@ -0,0 +1,626 @@
+import React, { useState, useMemo } from "react";
+import {
+ ScatterChart,
+ Scatter,
+ XAxis,
+ YAxis,
+ ZAxis,
+ CartesianGrid,
+ Tooltip,
+ ResponsiveContainer,
+ Cell,
+} from "recharts";
+import { getModelColor, modelSortOrder } from "../lib/colors";
+
+interface PCAPoint {
+ run_id: string;
+ short_id: string;
+ model: string;
+ score: number;
+ pc1: number;
+ pc2: number;
+ pc3: number;
+ config_summary: string;
+}
+
+interface PCALoading {
+ feature: string;
+ axis: string;
+ pc1: number;
+ pc2: number;
+ pc3: number;
+}
+
+interface PCAAxisImportance {
+ axis: string;
+ pc1: number;
+ pc2: number;
+ pc3: number;
+ total: number;
+}
+
+interface PCAData {
+ n_runs: number;
+ n_features: number;
+ n_components: number;
+ variance_explained: number[];
+ points: PCAPoint[];
+ loadings: PCALoading[];
+ axis_importance: PCAAxisImportance[];
+}
+
+interface PCAPlotProps {
+ data: PCAData;
+}
+
+type PCKey = "pc1" | "pc2" | "pc3";
+
+const PC_OPTIONS: { value: PCKey; label: string }[] = [
+ { value: "pc1", label: "PC1" },
+ { value: "pc2", label: "PC2" },
+ { value: "pc3", label: "PC3" },
+];
+
+const selectStyle: React.CSSProperties = {
+ background: "hsl(217 16% 15.5%)",
+ color: "hsl(213 14% 80%)",
+ border: "1px solid hsl(217 17% 28%)",
+ borderRadius: "0",
+ fontFamily: "'JetBrains Mono', monospace",
+ fontSize: "11px",
+ padding: "4px 6px",
+ cursor: "pointer",
+};
+
+const AXIS_LABELS: Record<string, string> = {
+ model: "Model",
+ effort: "Effort",
+ prompt_style: "Prompt Style",
+ language: "Language",
+ human_language: "Human Language",
+ tool_read: "Tool: Read",
+ tool_write: "Tool: Write",
+ tool_edit: "Tool: Edit",
+ tool_glob: "Tool: Glob",
+ tool_grep: "Tool: Grep",
+ linter: "Linter",
+ playwright: "Playwright",
+ context_file: "Context File",
+ web_search: "Web Search",
+ max_budget: "Budget",
+ tests_provided: "Tests Provided",
+ strategy: "Strategy",
+ design_guidance: "Design Guidance",
+ architecture: "Architecture",
+ error_checking: "Error Checking",
+ context_noise: "Context Noise",
+ renderer: "Renderer",
+ provider: "Provider",
+};
+
+function CustomTooltip({ active, payload }: any) {
+ if (!active || !payload || payload.length === 0) return null;
+ const d = payload[0]?.payload;
+ if (!d) return null;
+
+ const scorePct = Math.round(d.score * 100);
+ const scoreColor =
+ scorePct >= 70
+ ? "hsl(92 28% 65%)"
+ : scorePct >= 40
+ ? "hsl(40 71% 73%)"
+ : "hsl(355 52% 64%)";
+
+ return (
+ <div
+ style={{
+ background: "hsl(217 16% 15.5%)",
+ border: "1px solid hsl(217 17% 28%)",
+ borderRadius: "0",
+ fontFamily: "'JetBrains Mono', monospace",
+ fontSize: "11px",
+ padding: "8px 10px",
+ lineHeight: "1.6",
+ color: "hsl(213 14% 80%)",
+ maxWidth: 300,
+ }}
+ >
+ <div style={{ display: "flex", justifyContent: "space-between", gap: 12 }}>
+ <span style={{ fontWeight: 600, color: getModelColor(d.model) }}>
+ {d.model}
+ </span>
+ <span style={{ fontFamily: "'JetBrains Mono', monospace", fontWeight: 600, color: scoreColor }}>
+ {scorePct}%
+ </span>
+ </div>
+ <div style={{ marginTop: 4, color: "hsl(213 14% 55%)", fontSize: "10px" }}>
+ {d.short_id}
+ </div>
+ {d.config_summary && (
+ <div
+ style={{
+ marginTop: 4,
+ fontSize: "10px",
+ color: "hsl(213 14% 65%)",
+ wordBreak: "break-word",
+ }}
+ >
+ {d.config_summary}
+ </div>
+ )}
+ </div>
+ );
+}
+
+function LoadingsTable({
+ data,
+ pcKey,
+ varianceExplained,
+}: {
+ data: PCAData;
+ pcKey: PCKey;
+ varianceExplained: number;
+}) {
+ const pcIndex = parseInt(pcKey.replace("pc", "")) - 1;
+ const pcLabel = `PC${pcIndex + 1}`;
+
+ // Top 5 axes by importance for this PC
+ const topAxes = [...data.axis_importance]
+ .sort((a, b) => (b[pcKey] as number) - (a[pcKey] as number))
+ .slice(0, 5);
+
+ // For each top axis, find the most significant feature loadings
+ const axisDetails = topAxes.map((axEntry) => {
+ const axisLoadings = data.loadings
+ .filter((l) => l.axis === axEntry.axis)
+ .sort((a, b) => Math.abs(b[pcKey] as number) - Math.abs(a[pcKey] as number));
+ return {
+ axis: axEntry.axis,
+ label: AXIS_LABELS[axEntry.axis] || axEntry.axis,
+ importance: axEntry[pcKey] as number,
+ topFeatures: axisLoadings.slice(0, 3),
+ };
+ });
+
+ return (
+ <div>
+ <div
+ style={{
+ fontSize: "11px",
+ fontWeight: 600,
+ marginBottom: 6,
+ color: "hsl(213 14% 80%)",
+ }}
+ >
+ {pcLabel}{" "}
+ <span style={{ fontWeight: 400, color: "hsl(213 14% 55%)" }}>
+ ({varianceExplained.toFixed(1)}% variance)
+ </span>
+ </div>
+ <table
+ style={{
+ width: "100%",
+ borderCollapse: "collapse",
+ fontSize: "11px",
+ fontFamily: "'JetBrains Mono', monospace",
+ }}
+ >
+ <thead>
+ <tr
+ style={{
+ borderBottom: "1px solid hsl(217 17% 28%)",
+ color: "hsl(213 14% 55%)",
+ textAlign: "left",
+ }}
+ >
+ <th style={{ padding: "4px 8px 4px 0", fontWeight: 500 }}>Axis</th>
+ <th style={{ padding: "4px 8px", fontWeight: 500, textAlign: "right" }}>
+ Weight
+ </th>
+ <th style={{ padding: "4px 0 4px 8px", fontWeight: 500 }}>
+ Top Contributors
+ </th>
+ </tr>
+ </thead>
+ <tbody>
+ {axisDetails.map((ax) => (
+ <tr
+ key={ax.axis}
+ style={{ borderBottom: "1px solid hsl(217 17% 22%)" }}
+ >
+ <td style={{ padding: "4px 8px 4px 0", color: "hsl(213 14% 80%)" }}>
+ {ax.label}
+ </td>
+ <td
+ style={{
+ padding: "4px 8px",
+ textAlign: "right",
+ fontWeight: 600,
+ color: "hsl(193 44% 67%)",
+ }}
+ >
+ {ax.importance.toFixed(3)}
+ </td>
+ <td
+ style={{
+ padding: "4px 0 4px 8px",
+ color: "hsl(213 14% 55%)",
+ fontSize: "10px",
+ }}
+ >
+ {ax.topFeatures.map((f, i) => {
+ const val = f[pcKey] as number;
+ const color =
+ val > 0 ? "hsl(92 28% 65%)" : "hsl(355 52% 64%)";
+ return (
+ <span key={f.feature}>
+ {i > 0 && ", "}
+ <span style={{ color }}>
+ {val > 0 ? "+" : ""}
+ {val.toFixed(3)}
+ </span>{" "}
+ {f.feature.replace(`${ax.axis}_`, "")}
+ </span>
+ );
+ })}
+ </td>
+ </tr>
+ ))}
+ </tbody>
+ </table>
+ </div>
+ );
+}
+
+export default function PCAPlot({ data }: PCAPlotProps) {
+ const [xPC, setXPC] = useState<PCKey>("pc1");
+ const [yPC, setYPC] = useState<PCKey>("pc2");
+
+ // Group points by model
+ const modelGroups = useMemo(() => {
+ const groups: Record<string, PCAPoint[]> = {};
+ for (const pt of data.points) {
+ (groups[pt.model] ??= []).push(pt);
+ }
+ return Object.entries(groups).sort(
+ ([a], [b]) => modelSortOrder(a) - modelSortOrder(b)
+ );
+ }, [data.points]);
+
+ // Compute axis domains
+ const allX = data.points.map((p) => p[xPC]);
+ const allY = data.points.map((p) => p[yPC]);
+ const xMin = Math.min(...allX);
+ const xMax = Math.max(...allX);
+ const yMin = Math.min(...allY);
+ const yMax = Math.max(...allY);
+ const xPad = (xMax - xMin) * 0.08 || 1;
+ const yPad = (yMax - yMin) * 0.08 || 1;
+
+ // Score range for sizing
+ const scores = data.points.map((p) => p.score);
+ const minScore = Math.min(...scores);
+ const maxScore = Math.max(...scores);
+
+ const xVarIdx = parseInt(xPC.replace("pc", "")) - 1;
+ const yVarIdx = parseInt(yPC.replace("pc", "")) - 1;
+
+ return (
+ <div style={{ display: "flex", flexDirection: "column", gap: 24 }}>
+ {/* Chart card */}
+ <div className="card" style={{ position: "relative" }}>
+ <div
+ style={{
+ display: "flex",
+ alignItems: "center",
+ gap: 8,
+ marginBottom: 16,
+ flexWrap: "wrap",
+ }}
+ >
+ <span
+ style={{ fontSize: "11px", color: "hsl(213 14% 55%)", textTransform: "uppercase", letterSpacing: "0.5px" }}
+ >
+ X axis
+ </span>
+ <select
+ value={xPC}
+ onChange={(e) => setXPC(e.target.value as PCKey)}
+ style={selectStyle}
+ >
+ {PC_OPTIONS.map((opt) => (
+ <option key={opt.value} value={opt.value}>
+ {opt.label} ({data.variance_explained[parseInt(opt.value.replace("pc", "")) - 1]}%)
+ </option>
+ ))}
+ </select>
+ <span style={{ fontSize: "12px", color: "hsl(213 14% 55%)" }}>vs</span>
+ <span
+ style={{ fontSize: "11px", color: "hsl(213 14% 55%)", textTransform: "uppercase", letterSpacing: "0.5px" }}
+ >
+ Y axis
+ </span>
+ <select
+ value={yPC}
+ onChange={(e) => setYPC(e.target.value as PCKey)}
+ style={selectStyle}
+ >
+ {PC_OPTIONS.map((opt) => (
+ <option key={opt.value} value={opt.value}>
+ {opt.label} ({data.variance_explained[parseInt(opt.value.replace("pc", "")) - 1]}%)
+ </option>
+ ))}
+ </select>
+ <span
+ style={{
+ fontSize: "12px",
+ fontWeight: 400,
+ color: "hsl(213 14% 55%)",
+ marginLeft: 8,
+ }}
+ >
+ {data.n_runs} runs, {data.n_features} features
+ </span>
+ </div>
+
+ {/* Legend */}
+ <div
+ style={{
+ display: "flex",
+ gap: 12,
+ justifyContent: "center",
+ marginBottom: 12,
+ flexWrap: "wrap",
+ }}
+ >
+ {modelGroups.map(([model, pts]) => (
+ <div
+ key={model}
+ style={{
+ display: "flex",
+ alignItems: "center",
+ gap: 4,
+ fontSize: "11px",
+ fontFamily: "'JetBrains Mono', monospace",
+ }}
+ >
+ <div
+ style={{
+ width: 8,
+ height: 8,
+ background: getModelColor(model),
+ }}
+ />
+ <span style={{ color: getModelColor(model) }}>
+ {model}
+ </span>
+ <span style={{ color: "hsl(213 14% 45%)", fontSize: "10px" }}>
+ ({pts.length})
+ </span>
+ </div>
+ ))}
+ </div>
+
+ <ResponsiveContainer width="100%" height={420}>
+ <ScatterChart margin={{ top: 10, right: 20, bottom: 10, left: 10 }}>
+ <CartesianGrid
+ strokeDasharray="3 3"
+ stroke="hsl(217 17% 28%)"
+ />
+ <XAxis
+ dataKey="x"
+ name={`PC${xVarIdx + 1}`}
+ type="number"
+ domain={[xMin - xPad, xMax + xPad]}
+ stroke="hsl(213 14% 65%)"
+ fontSize={11}
+ tickFormatter={(v: number) => v.toFixed(1)}
+ label={{
+ value: `${xPC.toUpperCase()} (${data.variance_explained[xVarIdx]}%)`,
+ position: "insideBottom",
+ offset: -5,
+ style: {
+ fontSize: 11,
+ fill: "hsl(213 14% 55%)",
+ fontFamily: "'JetBrains Mono', monospace",
+ },
+ }}
+ />
+ <YAxis
+ dataKey="y"
+ name={`PC${yVarIdx + 1}`}
+ type="number"
+ domain={[yMin - yPad, yMax + yPad]}
+ stroke="hsl(213 14% 65%)"
+ fontSize={11}
+ tickFormatter={(v: number) => v.toFixed(1)}
+ label={{
+ value: `${yPC.toUpperCase()} (${data.variance_explained[yVarIdx]}%)`,
+ angle: -90,
+ position: "insideLeft",
+ style: {
+ fontSize: 11,
+ fill: "hsl(213 14% 55%)",
+ fontFamily: "'JetBrains Mono', monospace",
+ },
+ }}
+ />
+ <ZAxis
+ dataKey="z"
+ range={[40, 200]}
+ name="Score"
+ />
+ <Tooltip
+ content={<CustomTooltip />}
+ cursor={{ strokeDasharray: "3 3", stroke: "hsl(213 14% 35%)" }}
+ />
+ {modelGroups.map(([model, pts]) => {
+ const chartData = pts.map((p) => ({
+ x: p[xPC],
+ y: p[yPC],
+ z: maxScore > minScore
+ ? ((p.score - minScore) / (maxScore - minScore)) * 100
+ : 50,
+ score: p.score,
+ model: p.model,
+ short_id: p.short_id,
+ config_summary: p.config_summary,
+ run_id: p.run_id,
+ }));
+
+ return (
+ <Scatter
+ key={model}
+ name={model}
+ data={chartData}
+ fill={getModelColor(model)}
+ opacity={0.7}
+ isAnimationActive={false}
+ >
+ {chartData.map((_, idx) => (
+ <Cell
+ key={idx}
+ fill={getModelColor(model)}
+ stroke={getModelColor(model)}
+ strokeWidth={1}
+ opacity={0.7}
+ />
+ ))}
+ </Scatter>
+ );
+ })}
+ </ScatterChart>
+ </ResponsiveContainer>
+
+ <div
+ style={{
+ textAlign: "center",
+ fontSize: "10px",
+ color: "hsl(213 14% 45%)",
+ marginTop: 4,
+ }}
+ >
+ Point size proportional to score. Hover for details.
+ </div>
+ </div>
+
+ {/* Loadings interpretation card */}
+ <div className="card">
+ <h3
+ style={{
+ fontSize: "13px",
+ fontWeight: 600,
+ marginBottom: 16,
+ color: "hsl(213 14% 80%)",
+ textTransform: "uppercase",
+ letterSpacing: "0.5px",
+ }}
+ >
+ What do these dimensions mean?
+ </h3>
+ <p
+ style={{
+ fontSize: "11px",
+ color: "hsl(213 14% 55%)",
+ marginBottom: 16,
+ lineHeight: 1.6,
+ }}
+ >
+ Each principal component is a weighted combination of all configuration axes.
+ Higher weight means that axis contributes more to the variance in that dimension.
+ Green/red values show the direction: positive values push points right/up,
+ negative values push left/down.
+ </p>
+ <div
+ style={{
+ display: "grid",
+ gridTemplateColumns: "repeat(auto-fit, minmax(360px, 1fr))",
+ gap: 20,
+ }}
+ >
+ {(["pc1", "pc2", "pc3"] as PCKey[])
+ .slice(0, data.n_components)
+ .map((pc, idx) => (
+ <LoadingsTable
+ key={pc}
+ data={data}
+ pcKey={pc}
+ varianceExplained={data.variance_explained[idx]}
+ />
+ ))}
+ </div>
+ </div>
+
+ {/* Variance summary */}
+ <div className="card">
+ <h3
+ style={{
+ fontSize: "13px",
+ fontWeight: 600,
+ marginBottom: 12,
+ color: "hsl(213 14% 80%)",
+ textTransform: "uppercase",
+ letterSpacing: "0.5px",
+ }}
+ >
+ Variance Explained
+ </h3>
+ <div style={{ display: "flex", gap: 24, flexWrap: "wrap" }}>
+ {data.variance_explained.map((v, i) => {
+ const cumulative = data.variance_explained
+ .slice(0, i + 1)
+ .reduce((a, b) => a + b, 0);
+ return (
+ <div key={i} style={{ flex: "1 1 100px" }}>
+ <div
+ style={{
+ display: "flex",
+ justifyContent: "space-between",
+ fontSize: "11px",
+ marginBottom: 4,
+ }}
+ >
+ <span style={{ color: "hsl(213 14% 80%)" }}>PC{i + 1}</span>
+ <span
+ style={{
+ fontFamily: "'JetBrains Mono', monospace",
+ fontWeight: 600,
+ color: "hsl(193 44% 67%)",
+ }}
+ >
+ {v.toFixed(1)}%
+ </span>
+ </div>
+ <div
+ style={{
+ background: "hsl(216 15% 19%)",
+ height: 6,
+ overflow: "hidden",
+ }}
+ >
+ <div
+ style={{
+ width: `${v}%`,
+ height: "100%",
+ background: "hsl(193 44% 67%)",
+ }}
+ />
+ </div>
+ <div
+ style={{
+ fontSize: "10px",
+ color: "hsl(213 14% 45%)",
+ marginTop: 2,
+ textAlign: "right",
+ }}
+ >
+ cumulative: {cumulative.toFixed(1)}%
+ </div>
+ </div>
+ );
+ })}
+ </div>
+ </div>
+ </div>
+ );
+}
diff --git a/dashboard/src/components/VariabilityViolin.tsx b/dashboard/src/components/VariabilityViolin.tsx
@@ -378,19 +378,8 @@ export default function VariabilityViolin({ runs }: VariabilityViolinProps) {
<Cell key={entry.label} fill={entry.color} />
))}
</Bar>
- {/* Jittered scatter dots for individual cell CV values */}
- <Scatter
- data={scatterData}
- dataKey="cv"
- yAxisId="cv"
- fill={SMUI.frost2}
- fillOpacity={0.6}
- >
- <ZAxis range={[50, 50]} />
- {scatterData.map((pt, i) => (
- <Cell key={i} fill={pt.color} fillOpacity={0.6} />
- ))}
- </Scatter>
+ {/* Hidden scatter to keep recharts scale consistent */}
+ <Scatter data={[]} dataKey="cv" yAxisId="cv" fill="transparent" />
</ComposedChart>
</ResponsiveContainer>
</div>
diff --git a/dashboard/src/pages/pca.astro b/dashboard/src/pages/pca.astro
@@ -0,0 +1,27 @@
+---
+import Base from "../layouts/Base.astro";
+import PCAPlot from "../components/PCAPlot";
+import fs from "node:fs";
+import path from "node:path";
+
+const pcaPath = path.resolve(process.cwd(), "../results/analysis/pca.json");
+let pcaData = null;
+if (fs.existsSync(pcaPath)) {
+ pcaData = JSON.parse(fs.readFileSync(pcaPath, "utf-8"));
+}
+---
+
+<Base title="PCA">
+ <h1 style="margin-bottom: 8px;">Principal Component Analysis</h1>
+ <p style="color: var(--text-muted); margin-bottom: 24px; font-size: 11px; text-transform: uppercase; letter-spacing: 0.5px;">
+ Dimensionality reduction of the configuration space. Which axes drive the most variance?
+ </p>
+
+ {pcaData ? (
+ <PCAPlot client:load data={pcaData} />
+ ) : (
+ <div class="card" style="text-align: center; padding: 40px; color: var(--text-muted);">
+ No PCA data yet. Run <code>python3 harness/pca-analysis.py</code> to generate.
+ </div>
+ )}
+</Base>
diff --git a/harness/pca-analysis.py b/harness/pca-analysis.py
@@ -0,0 +1,265 @@
+#!/usr/bin/env python3
+"""PCA analysis of benchmark runs.
+
+Loads all runs, one-hot encodes categorical axis values, runs PCA with
+3 components, and saves results to results/analysis/pca.json.
+
+Usage:
+ python3 harness/pca-analysis.py
+"""
+
+import json
+import sys
+from pathlib import Path
+
+import numpy as np
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
+PROJECT_DIR = Path(__file__).resolve().parent.parent
+RESULTS_DIR = PROJECT_DIR / "results"
+RUNS_DIR = RESULTS_DIR / "runs"
+OUTPUT_PATH = RESULTS_DIR / "analysis" / "pca.json"
+
+# Axes to include in PCA (must match meta.json keys)
+AXES = [
+ "model",
+ "effort",
+ "prompt_style",
+ "language",
+ "human_language",
+ "tool_read",
+ "tool_write",
+ "tool_edit",
+ "tool_glob",
+ "tool_grep",
+ "linter",
+ "playwright",
+ "context_file",
+ "web_search",
+ "max_budget",
+ "tests_provided",
+ "strategy",
+ "design_guidance",
+ "architecture",
+ "error_checking",
+ "context_noise",
+ "renderer",
+ "provider",
+]
+
+# Defaults for axes that may not exist in older runs
+AXIS_DEFAULTS = {
+ "strategy": "none",
+ "tests_provided": "none",
+ "design_guidance": "none",
+ "architecture": "none",
+ "error_checking": "none",
+ "context_noise": "clean",
+ "renderer": "none",
+ "provider": "anthropic",
+}
+
+# Normalize old schema values (same as dashboard data.ts)
+def normalize_meta(meta: dict) -> dict:
+ if meta.get("sub_agents") and not meta.get("strategy"):
+ meta["strategy"] = "use_subagents" if meta["sub_agents"] == "on" else "none"
+ if meta.get("playwright") == "on":
+ meta["playwright"] = "available"
+ for key, default in AXIS_DEFAULTS.items():
+ if key not in meta or meta[key] is None:
+ meta[key] = default
+ return meta
+
+
+def load_runs() -> list[dict]:
+ """Load all runs that have both meta.json and eval_results.json with a score."""
+ runs = []
+ if not RUNS_DIR.exists():
+ return runs
+
+ for run_dir in sorted(RUNS_DIR.iterdir()):
+ if not run_dir.is_dir():
+ continue
+ meta_path = run_dir / "meta.json"
+ eval_path = run_dir / "eval_results.json"
+ if not meta_path.exists() or not eval_path.exists():
+ continue
+
+ try:
+ meta = json.loads(meta_path.read_text())
+ meta = normalize_meta(meta)
+ eval_results = json.loads(eval_path.read_text())
+ score = eval_results.get("score")
+ if score is None:
+ continue
+ runs.append({
+ "meta": meta,
+ "score": float(score),
+ "run_id": meta.get("run_id", run_dir.name),
+ "short_id": meta.get("short_id", run_dir.name[:8]),
+ })
+ except (json.JSONDecodeError, ValueError):
+ continue
+
+ return runs
+
+
+def build_feature_matrix(runs: list[dict]) -> tuple[np.ndarray, list[str], list[str], dict[str, list[str]]]:
+ """One-hot encode all axis values.
+
+ Returns:
+ matrix: (n_runs, n_features) array
+ feature_names: list of feature names like "model_haiku"
+ axis_for_feature: which axis each feature belongs to
+ axis_features: mapping from axis name to list of feature names
+ """
+ # Collect all unique values per axis
+ axis_values: dict[str, set[str]] = {ax: set() for ax in AXES}
+ for run in runs:
+ for ax in AXES:
+ val = str(run["meta"].get(ax, AXIS_DEFAULTS.get(ax, "unknown")))
+ axis_values[ax].add(val)
+
+ # Sort values for determinism
+ axis_sorted: dict[str, list[str]] = {
+ ax: sorted(vals) for ax, vals in axis_values.items()
+ }
+
+ # Skip axes with only one unique value (no variance to explain)
+ active_axes = {ax: vals for ax, vals in axis_sorted.items() if len(vals) > 1}
+ skipped = [ax for ax in AXES if ax not in active_axes]
+ if skipped:
+ print(f" Skipping constant axes: {', '.join(skipped)}")
+
+ # Build feature names and axis mapping
+ feature_names: list[str] = []
+ axis_for_feature: list[str] = []
+ axis_features: dict[str, list[str]] = {}
+
+ for ax, vals in active_axes.items():
+ axis_features[ax] = []
+ for val in vals:
+ fname = f"{ax}_{val}"
+ feature_names.append(fname)
+ axis_for_feature.append(ax)
+ axis_features[ax].append(fname)
+
+ # Build the matrix
+ n_runs = len(runs)
+ n_features = len(feature_names)
+ matrix = np.zeros((n_runs, n_features), dtype=np.float64)
+
+ for i, run in enumerate(runs):
+ for ax, vals in active_axes.items():
+ run_val = str(run["meta"].get(ax, AXIS_DEFAULTS.get(ax, "unknown")))
+ for val in vals:
+ fname = f"{ax}_{val}"
+ j = feature_names.index(fname)
+ matrix[i, j] = 1.0 if run_val == val else 0.0
+
+ return matrix, feature_names, axis_for_feature, axis_features
+
+
+def run_pca(runs: list[dict]) -> dict:
+ """Run PCA and return structured results."""
+ matrix, feature_names, axis_for_feature, axis_features = build_feature_matrix(runs)
+
+ n_runs, n_features = matrix.shape
+ n_components = min(3, n_features, n_runs)
+
+ print(f" {n_runs} runs, {n_features} features, {n_components} components")
+
+ # Standardize features (zero mean, unit variance)
+ scaler = StandardScaler()
+ matrix_scaled = scaler.fit_transform(matrix)
+
+ # Run PCA
+ pca = PCA(n_components=n_components)
+ transformed = pca.fit_transform(matrix_scaled)
+
+ # Variance explained
+ variance_explained = [round(float(v) * 100, 2) for v in pca.explained_variance_ratio_]
+ print(f" Variance explained: {variance_explained}")
+
+ # Points (one per run)
+ pc_labels = [f"pc{i+1}" for i in range(n_components)]
+ points = []
+ for i, run in enumerate(runs):
+ point = {
+ "run_id": run["run_id"],
+ "short_id": run["short_id"],
+ "model": run["meta"].get("model", "unknown"),
+ "score": round(run["score"], 4),
+ }
+ for j, label in enumerate(pc_labels):
+ point[label] = round(float(transformed[i, j]), 4)
+ # Add a config summary for tooltip
+ summary_parts = []
+ for ax in ["effort", "prompt_style", "language", "max_budget", "strategy"]:
+ val = run["meta"].get(ax, "")
+ if val and val != "none":
+ summary_parts.append(f"{ax}={val}")
+ point["config_summary"] = ", ".join(summary_parts)
+ points.append(point)
+
+ # Raw loadings (one per feature per PC)
+ loadings = []
+ for j, fname in enumerate(feature_names):
+ loading = {
+ "feature": fname,
+ "axis": axis_for_feature[j],
+ }
+ for k, label in enumerate(pc_labels):
+ loading[label] = round(float(pca.components_[k, j]), 4)
+ loadings.append(loading)
+
+ # Axis-level summaries: sum of absolute loadings per axis per PC
+ axis_importance: list[dict] = []
+ for ax, fnames in axis_features.items():
+ entry: dict = {"axis": ax}
+ for k, label in enumerate(pc_labels):
+ total = 0.0
+ for fname in fnames:
+ j = feature_names.index(fname)
+ total += abs(float(pca.components_[k, j]))
+ entry[label] = round(total, 4)
+ axis_importance.append(entry)
+
+ # Sort by total importance across all PCs
+ for entry in axis_importance:
+ entry["total"] = round(sum(entry[label] for label in pc_labels), 4)
+ axis_importance.sort(key=lambda x: x["total"], reverse=True)
+
+ return {
+ "n_runs": n_runs,
+ "n_features": n_features,
+ "n_components": n_components,
+ "variance_explained": variance_explained,
+ "points": points,
+ "loadings": loadings,
+ "axis_importance": axis_importance,
+ }
+
+
+def main():
+ print("PCA Analysis")
+ print("=" * 40)
+
+ runs = load_runs()
+ if len(runs) < 3:
+ print(f" Only {len(runs)} runs with scores found. Need at least 3 for PCA.")
+ sys.exit(1)
+
+ print(f" Loaded {len(runs)} runs with scores")
+
+ results = run_pca(runs)
+
+ OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
+ OUTPUT_PATH.write_text(json.dumps(results, indent=2))
+ print(f"\n Saved to {OUTPUT_PATH}")
+ print(" Done.")
+
+
+if __name__ == "__main__":
+ main()
diff --git a/results/analysis/pca.json b/results/analysis/pca.json
@@ -0,0 +1,3087 @@
+{
+ "n_runs": 263,
+ "n_features": 45,
+ "n_components": 3,
+ "variance_explained": [
+ 14.65,
+ 12.69,
+ 5.8
+ ],
+ "points": [
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "85cfb3b7",
+ "model": "glm-4.7",
+ "score": 0.33,
+ "pc1": 3.9991,
+ "pc2": -0.0931,
+ "pc3": -0.0593,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "c530817e",
+ "model": "glm-4.7",
+ "score": 0.38,
+ "pc1": 3.9991,
+ "pc2": -0.0931,
+ "pc3": -0.0593,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "5ea5d539",
+ "model": "glm-5.1",
+ "score": 0.38,
+ "pc1": 4.0634,
+ "pc2": -0.1696,
+ "pc3": 0.2812,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f2ff7829",
+ "model": "glm-5.1",
+ "score": 0.35,
+ "pc1": 4.0634,
+ "pc2": -0.1696,
+ "pc3": 0.2812,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "6b848132",
+ "model": "glm-5.1",
+ "score": 0.305,
+ "pc1": 4.0634,
+ "pc2": -0.1696,
+ "pc3": 0.2812,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "e047cf3a",
+ "model": "haiku",
+ "score": 0.885,
+ "pc1": -0.7066,
+ "pc2": 2.4629,
+ "pc3": 0.5213,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "5ae88633",
+ "model": "haiku",
+ "score": 0.5,
+ "pc1": -0.7066,
+ "pc2": 2.4629,
+ "pc3": 0.5213,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "1d08ee76",
+ "model": "haiku",
+ "score": 0.5,
+ "pc1": -0.7066,
+ "pc2": 2.4629,
+ "pc3": 0.5213,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "fe66c902",
+ "model": "opus",
+ "score": 0.355,
+ "pc1": -0.4687,
+ "pc2": 3.0361,
+ "pc3": 0.8396,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f437a754",
+ "model": "opus",
+ "score": 0.47,
+ "pc1": -0.4687,
+ "pc2": 3.0361,
+ "pc3": 0.8396,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "6f157de1",
+ "model": "opus",
+ "score": 0.77,
+ "pc1": -0.4687,
+ "pc2": 3.0361,
+ "pc3": 0.8396,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "aec24c80",
+ "model": "sonnet",
+ "score": 0.425,
+ "pc1": -0.4587,
+ "pc2": 3.0321,
+ "pc3": 0.8381,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f451b3e8",
+ "model": "sonnet",
+ "score": 0.43,
+ "pc1": -0.4587,
+ "pc2": 3.0321,
+ "pc3": 0.8381,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "59fdb0fc",
+ "model": "sonnet",
+ "score": 0.5,
+ "pc1": -0.4587,
+ "pc2": 3.0321,
+ "pc3": 0.8381,
+ "config_summary": "effort=high, prompt_style=simple, language=javascript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run1",
+ "short_id": "dcbf6400",
+ "model": "haiku",
+ "score": 0.53,
+ "pc1": -4.3682,
+ "pc2": -5.48,
+ "pc3": 0.1702,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=high_model=haiku_pw=off_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=off_tread=off_twrite=on_web=on_run3",
+ "short_id": "b13fad58",
+ "model": "haiku",
+ "score": 0.425,
+ "pc1": -4.3682,
+ "pc2": -5.48,
+ "pc3": 0.1702,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm45air_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "cbd2d1e2",
+ "model": "glm-4.5-air",
+ "score": 0.35,
+ "pc1": 1.6075,
+ "pc2": -4.6655,
+ "pc3": 1.8639,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "f76992f1",
+ "model": "glm-4.7",
+ "score": 0.305,
+ "pc1": 1.6787,
+ "pc2": -4.699,
+ "pc3": 1.822,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "413c1f93",
+ "model": "glm-4.7",
+ "score": 0.795,
+ "pc1": 2.2238,
+ "pc2": -3.6573,
+ "pc3": 0.679,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "9a9774f0",
+ "model": "glm-4.7",
+ "score": 0.37,
+ "pc1": 3.0819,
+ "pc2": -2.1239,
+ "pc3": 0.3539,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "4a154f54",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 3.0819,
+ "pc2": -2.1239,
+ "pc3": 0.3539,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "05601da1",
+ "model": "glm-5.1",
+ "score": 0.305,
+ "pc1": 1.743,
+ "pc2": -4.7754,
+ "pc3": 2.1625,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "a6d9fb9c",
+ "model": "glm-5.1",
+ "score": 0.355,
+ "pc1": 2.2881,
+ "pc2": -3.7337,
+ "pc3": 1.0196,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "7c167ef9",
+ "model": "glm-5.1",
+ "score": 0.255,
+ "pc1": 3.1462,
+ "pc2": -2.2003,
+ "pc3": 0.6944,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "cce71fd1",
+ "model": "glm-5.1",
+ "score": 0.33,
+ "pc1": 3.1462,
+ "pc2": -2.2003,
+ "pc3": 0.6944,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "9b785a51",
+ "model": "glm-5.1",
+ "score": 0.65,
+ "pc1": 3.1462,
+ "pc2": -2.2003,
+ "pc3": 0.6944,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "062f01a0",
+ "model": "haiku",
+ "score": 0.19,
+ "pc1": -1.6238,
+ "pc2": 0.4321,
+ "pc3": 0.9345,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "586c6b0a",
+ "model": "haiku",
+ "score": 0.405,
+ "pc1": -1.6238,
+ "pc2": 0.4321,
+ "pc3": 0.9345,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "71fa204f",
+ "model": "haiku",
+ "score": 0.68,
+ "pc1": -1.6238,
+ "pc2": 0.4321,
+ "pc3": 0.9345,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=detailed_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "c151a356",
+ "model": "haiku",
+ "score": 0.5,
+ "pc1": -0.786,
+ "pc2": -3.9898,
+ "pc3": 2.1591,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run1",
+ "short_id": "b29d066e",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -4.4636,
+ "pc2": -9.1774,
+ "pc3": 3.047,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run2",
+ "short_id": "1e13c72f",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -4.4636,
+ "pc2": -9.1774,
+ "pc3": 3.047,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run3",
+ "short_id": "56088123",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -4.4636,
+ "pc2": -9.1774,
+ "pc3": 3.047,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "1fdd595b",
+ "model": "haiku",
+ "score": 0.355,
+ "pc1": -0.2408,
+ "pc2": -2.9481,
+ "pc3": 1.0162,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "bd51c309",
+ "model": "opus",
+ "score": 0.49,
+ "pc1": -1.3859,
+ "pc2": 1.0053,
+ "pc3": 1.2528,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "d184704b",
+ "model": "opus",
+ "score": 0.915,
+ "pc1": -1.3859,
+ "pc2": 1.0053,
+ "pc3": 1.2528,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "135b43a3",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -1.3859,
+ "pc2": 1.0053,
+ "pc3": 1.2528,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "05536f95",
+ "model": "sonnet",
+ "score": 0.37,
+ "pc1": -1.3759,
+ "pc2": 1.0013,
+ "pc3": 1.2513,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f8a57948",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.3759,
+ "pc2": 1.0013,
+ "pc3": 1.2513,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "69bb8919",
+ "model": "sonnet",
+ "score": 0.835,
+ "pc1": -1.3759,
+ "pc2": 1.0013,
+ "pc3": 1.2513,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "1f33a77b",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 2.8901,
+ "pc2": -0.8386,
+ "pc3": -3.6109,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "f2b6194f",
+ "model": "glm-4.7",
+ "score": 0.595,
+ "pc1": 2.8901,
+ "pc2": -0.8386,
+ "pc3": -3.6109,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "004dc1a5",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -1.8156,
+ "pc2": 1.7175,
+ "pc3": -3.0304,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "95414e63",
+ "model": "haiku",
+ "score": 0.34,
+ "pc1": -1.8156,
+ "pc2": 1.7175,
+ "pc3": -3.0304,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "805f705d",
+ "model": "haiku",
+ "score": 0.405,
+ "pc1": -1.8156,
+ "pc2": 1.7175,
+ "pc3": -3.0304,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "b51daba4",
+ "model": "opus",
+ "score": 0.835,
+ "pc1": -1.5777,
+ "pc2": 2.2907,
+ "pc3": -2.712,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "c946c543",
+ "model": "opus",
+ "score": 0.49,
+ "pc1": -1.5777,
+ "pc2": 2.2907,
+ "pc3": -2.712,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "66d681fb",
+ "model": "opus",
+ "score": 0.835,
+ "pc1": -1.5777,
+ "pc2": 2.2907,
+ "pc3": -2.712,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "671816fb",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.5677,
+ "pc2": 2.2867,
+ "pc3": -2.7135,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "4ba3ba91",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.5677,
+ "pc2": 2.2867,
+ "pc3": -2.7135,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "d7998414",
+ "model": "sonnet",
+ "score": 0.19,
+ "pc1": -1.5677,
+ "pc2": 2.2867,
+ "pc3": -2.7135,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "50989696",
+ "model": "glm-4.5-air",
+ "score": 0.305,
+ "pc1": 2.3953,
+ "pc2": 0.1992,
+ "pc3": -0.0859,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "1c26e1d8",
+ "model": "glm-4.5-air",
+ "score": 0.305,
+ "pc1": 2.3953,
+ "pc2": 0.1992,
+ "pc3": -0.0859,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3",
+ "short_id": "5141dfbf",
+ "model": "glm-4.5-air",
+ "score": 0.305,
+ "pc1": 2.6642,
+ "pc2": -1.9691,
+ "pc3": -1.3804,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "3f7bdd4d",
+ "model": "glm-4.5-air",
+ "score": 0.33,
+ "pc1": 3.5139,
+ "pc2": -0.7022,
+ "pc3": -0.4263,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "456d514c",
+ "model": "glm-4.5-air",
+ "score": 0.155,
+ "pc1": 3.5139,
+ "pc2": -0.7022,
+ "pc3": -0.4263,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "9bdf645c",
+ "model": "glm-4.5-air",
+ "score": 0.155,
+ "pc1": 3.5139,
+ "pc2": -0.7022,
+ "pc3": -0.4263,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "fa2674ac",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 2.4665,
+ "pc2": 0.1657,
+ "pc3": -0.1278,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "c22109f8",
+ "model": "glm-4.7",
+ "score": 0.06,
+ "pc1": 3.5732,
+ "pc2": -0.3453,
+ "pc3": -0.486,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "56afde62",
+ "model": "glm-4.7",
+ "score": 0.305,
+ "pc1": 3.04,
+ "pc2": -1.7773,
+ "pc3": 0.6747,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "6a743388",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 3.5884,
+ "pc2": -0.3184,
+ "pc3": -0.8607,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=creative_validate"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "af5e84fc",
+ "model": "glm-4.7",
+ "score": 0.305,
+ "pc1": 3.5884,
+ "pc2": -0.3184,
+ "pc3": -0.8607,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=creative_validate"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "2f761815",
+ "model": "glm-4.7",
+ "score": 0.355,
+ "pc1": 3.5884,
+ "pc2": -0.3184,
+ "pc3": -0.8607,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=creative_validate"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "e0237626",
+ "model": "glm-4.7",
+ "score": 0.34,
+ "pc1": 3.5834,
+ "pc2": -0.3178,
+ "pc3": -0.8565,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=iterate"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "31a529dc",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 2.7141,
+ "pc2": -2.0444,
+ "pc3": -0.7343,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1",
+ "short_id": "6a018f5e",
+ "model": "glm-4.7",
+ "score": 0.19,
+ "pc1": 2.7912,
+ "pc2": -1.9908,
+ "pc3": 0.0428,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3",
+ "short_id": "ed0b0147",
+ "model": "glm-4.7",
+ "score": 0.255,
+ "pc1": 2.7912,
+ "pc2": -1.9908,
+ "pc3": 0.0428,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2",
+ "short_id": "e8d32946",
+ "model": "glm-4.7",
+ "score": 0.29,
+ "pc1": 2.7354,
+ "pc2": -2.0026,
+ "pc3": -1.4223,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "0a030357",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 3.5851,
+ "pc2": -0.7356,
+ "pc3": -0.4682,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "fd037e18",
+ "model": "glm-4.7",
+ "score": 0.34,
+ "pc1": 3.5851,
+ "pc2": -0.7356,
+ "pc3": -0.4682,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "ad716871",
+ "model": "glm-4.7",
+ "score": 0.155,
+ "pc1": 3.5851,
+ "pc2": -0.7356,
+ "pc3": -0.4682,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "7c7dfa27",
+ "model": "glm-5.1",
+ "score": 0.03,
+ "pc1": 2.5308,
+ "pc2": 0.0893,
+ "pc3": 0.2127,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "5afe9b8e",
+ "model": "glm-5.1",
+ "score": 0.03,
+ "pc1": 2.5308,
+ "pc2": 0.0893,
+ "pc3": 0.2127,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "7e2cf342",
+ "model": "glm-5.1",
+ "score": 0.355,
+ "pc1": 2.5308,
+ "pc2": 0.0893,
+ "pc3": 0.2127,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "6abf96c7",
+ "model": "glm-5.1",
+ "score": 0.155,
+ "pc1": 3.1043,
+ "pc2": -1.8537,
+ "pc3": 1.0152,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "8bcd3ae0",
+ "model": "glm-5.1",
+ "score": 0.305,
+ "pc1": 3.1043,
+ "pc2": -1.8537,
+ "pc3": 1.0152,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "496e0334",
+ "model": "glm-5.1",
+ "score": 0.155,
+ "pc1": 3.1043,
+ "pc2": -1.8537,
+ "pc3": 1.0152,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "11b37482",
+ "model": "glm-5.1",
+ "score": 0.705,
+ "pc1": 5.269,
+ "pc2": -1.2587,
+ "pc3": -0.5692,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "63c0c2ab",
+ "model": "glm-5.1",
+ "score": 0.8,
+ "pc1": 5.269,
+ "pc2": -1.2587,
+ "pc3": -0.5692,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "5da14018",
+ "model": "glm-5.1",
+ "score": 0.305,
+ "pc1": 5.269,
+ "pc2": -1.2587,
+ "pc3": -0.5692,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "140cba7f",
+ "model": "glm-5.1",
+ "score": 0.33,
+ "pc1": 2.7784,
+ "pc2": -2.1208,
+ "pc3": -0.3938,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "06c93bc4",
+ "model": "glm-5.1",
+ "score": 0.33,
+ "pc1": 2.7784,
+ "pc2": -2.1208,
+ "pc3": -0.3938,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "6a89452c",
+ "model": "glm-5.1",
+ "score": 0.255,
+ "pc1": 2.7784,
+ "pc2": -2.1208,
+ "pc3": -0.3938,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "5e2f9389",
+ "model": "glm-5.1",
+ "score": 0.155,
+ "pc1": 2.8992,
+ "pc2": -1.9082,
+ "pc3": 1.2813,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "6cf8d774",
+ "model": "glm-5.1",
+ "score": 0.73,
+ "pc1": 2.8992,
+ "pc2": -1.9082,
+ "pc3": 1.2813,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "61f8b45c",
+ "model": "glm-5.1",
+ "score": 0.305,
+ "pc1": 2.8992,
+ "pc2": -1.9082,
+ "pc3": 1.2813,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1",
+ "short_id": "b1e752d7",
+ "model": "glm-5.1",
+ "score": 0.385,
+ "pc1": 2.8555,
+ "pc2": -2.0673,
+ "pc3": 0.3833,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2",
+ "short_id": "ad47b58e",
+ "model": "glm-5.1",
+ "score": 0.37,
+ "pc1": 2.8555,
+ "pc2": -2.0673,
+ "pc3": 0.3833,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3",
+ "short_id": "689ef4b4",
+ "model": "glm-5.1",
+ "score": 0.385,
+ "pc1": 2.8555,
+ "pc2": -2.0673,
+ "pc3": 0.3833,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1",
+ "short_id": "5e839ecf",
+ "model": "glm-5.1",
+ "score": 0.34,
+ "pc1": 2.6914,
+ "pc2": -2.1142,
+ "pc3": 1.2034,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2",
+ "short_id": "40e70ba8",
+ "model": "glm-5.1",
+ "score": 0.355,
+ "pc1": 2.6914,
+ "pc2": -2.1142,
+ "pc3": 1.2034,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3",
+ "short_id": "2d900db2",
+ "model": "glm-5.1",
+ "score": 0.225,
+ "pc1": 2.6914,
+ "pc2": -2.1142,
+ "pc3": 1.2034,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1",
+ "short_id": "dec1df41",
+ "model": "glm-5.1",
+ "score": 0.29,
+ "pc1": 2.7997,
+ "pc2": -2.079,
+ "pc3": -1.0817,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2",
+ "short_id": "7165dc1a",
+ "model": "glm-5.1",
+ "score": 0.295,
+ "pc1": 2.7997,
+ "pc2": -2.079,
+ "pc3": -1.0817,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3",
+ "short_id": "b656c546",
+ "model": "glm-5.1",
+ "score": 0.255,
+ "pc1": 2.7997,
+ "pc2": -2.079,
+ "pc3": -1.0817,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "71d588fb",
+ "model": "glm-5.1",
+ "score": 0.78,
+ "pc1": 3.6494,
+ "pc2": -0.812,
+ "pc3": -0.1277,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "781c564b",
+ "model": "glm-5.1",
+ "score": 0.38,
+ "pc1": 3.6494,
+ "pc2": -0.812,
+ "pc3": -0.1277,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "3e9975cb",
+ "model": "glm-5.1",
+ "score": 0.33,
+ "pc1": 3.6494,
+ "pc2": -0.812,
+ "pc3": -0.1277,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "14486646",
+ "model": "glm-5.1",
+ "score": 0.365,
+ "pc1": 5.2617,
+ "pc2": -1.2567,
+ "pc3": -0.5664,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "cbbff570",
+ "model": "haiku",
+ "score": 0.515,
+ "pc1": -1.6657,
+ "pc2": 0.7788,
+ "pc3": 1.2553,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "62c70152",
+ "model": "haiku",
+ "score": 0.34,
+ "pc1": -1.6657,
+ "pc2": 0.7788,
+ "pc3": 1.2553,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "80f1c3d5",
+ "model": "haiku",
+ "score": 0.565,
+ "pc1": -1.6657,
+ "pc2": 0.7788,
+ "pc3": 1.2553,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "a30100ff",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": 0.0019,
+ "pc2": 0.8749,
+ "pc3": 0.2093,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "b61f8d31",
+ "model": "haiku",
+ "score": 0.68,
+ "pc1": 0.0019,
+ "pc2": 0.8749,
+ "pc3": 0.2093,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "645e0c8f",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": 0.0019,
+ "pc2": 0.8749,
+ "pc3": 0.2093,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "188635cc",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -1.9915,
+ "pc2": 0.5117,
+ "pc3": -0.1537,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "9805c24a",
+ "model": "haiku",
+ "score": 0.565,
+ "pc1": -1.9915,
+ "pc2": 0.5117,
+ "pc3": -0.1537,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "5cdb89b6",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -1.9915,
+ "pc2": 0.5117,
+ "pc3": -0.1537,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "4949d521",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -1.8708,
+ "pc2": 0.7243,
+ "pc3": 1.5213,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "165fb66f",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -1.8708,
+ "pc2": 0.7243,
+ "pc3": 1.5213,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "af738eee",
+ "model": "haiku",
+ "score": 0.28,
+ "pc1": -1.8708,
+ "pc2": 0.7243,
+ "pc3": 1.5213,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1",
+ "short_id": "da87903f",
+ "model": "haiku",
+ "score": 0.755,
+ "pc1": -1.9145,
+ "pc2": 0.5652,
+ "pc3": 0.6233,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2",
+ "short_id": "49012037",
+ "model": "haiku",
+ "score": 0.315,
+ "pc1": -1.9145,
+ "pc2": 0.5652,
+ "pc3": 0.6233,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3",
+ "short_id": "4b5f4543",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -1.9145,
+ "pc2": 0.5652,
+ "pc3": 0.6233,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1",
+ "short_id": "37c69c60",
+ "model": "haiku",
+ "score": 0.19,
+ "pc1": -2.0785,
+ "pc2": 0.5182,
+ "pc3": 1.4434,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2",
+ "short_id": "77c2245c",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -2.0785,
+ "pc2": 0.5182,
+ "pc3": 1.4434,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3",
+ "short_id": "fe986bd0",
+ "model": "haiku",
+ "score": 0.405,
+ "pc1": -2.0785,
+ "pc2": 0.5182,
+ "pc3": 1.4434,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1",
+ "short_id": "0d40c124",
+ "model": "haiku",
+ "score": 0.87,
+ "pc1": -1.9703,
+ "pc2": 0.5534,
+ "pc3": -0.8417,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2",
+ "short_id": "4d6ff9c9",
+ "model": "haiku",
+ "score": 0.34,
+ "pc1": -1.9703,
+ "pc2": 0.5534,
+ "pc3": -0.8417,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3",
+ "short_id": "1a5b849b",
+ "model": "haiku",
+ "score": 0.405,
+ "pc1": -1.9703,
+ "pc2": 0.5534,
+ "pc3": -0.8417,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "e01fbfa7",
+ "model": "haiku",
+ "score": 0.33,
+ "pc1": -1.9786,
+ "pc2": 0.287,
+ "pc3": 0.4375,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2",
+ "short_id": "bf5c394f",
+ "model": "haiku",
+ "score": 0.875,
+ "pc1": -1.9786,
+ "pc2": 0.287,
+ "pc3": 0.4375,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "4bdcef51",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -1.1205,
+ "pc2": 1.8204,
+ "pc3": 0.1124,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "4db28f22",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -1.1205,
+ "pc2": 1.8204,
+ "pc3": 0.1124,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "6b13f05b",
+ "model": "haiku",
+ "score": 0.675,
+ "pc1": -1.1205,
+ "pc2": 1.8204,
+ "pc3": 0.1124,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "79675074",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": 1.1205,
+ "pc2": -0.0264,
+ "pc3": -0.1311,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "c0d3fd49",
+ "model": "haiku",
+ "score": 0.34,
+ "pc1": 1.1205,
+ "pc2": -0.0264,
+ "pc3": -0.1311,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "1fbd2965",
+ "model": "haiku",
+ "score": 0.34,
+ "pc1": 1.1205,
+ "pc2": -0.0264,
+ "pc3": -0.1311,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "c9b0a190",
+ "model": "haiku",
+ "score": 0.76,
+ "pc1": -0.0019,
+ "pc2": 0.919,
+ "pc3": -0.2281,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "c31b514e",
+ "model": "haiku",
+ "score": 0.715,
+ "pc1": -0.0019,
+ "pc2": 0.919,
+ "pc3": -0.2281,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "8de1a3c2",
+ "model": "haiku",
+ "score": 0.415,
+ "pc1": -0.0019,
+ "pc2": 0.919,
+ "pc3": -0.2281,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "9cd7d12a",
+ "model": "opus",
+ "score": 0.305,
+ "pc1": -1.4278,
+ "pc2": 1.3519,
+ "pc3": 1.5736,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "28abb304",
+ "model": "opus",
+ "score": 0.205,
+ "pc1": -1.4278,
+ "pc2": 1.3519,
+ "pc3": 1.5736,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "30bc2917",
+ "model": "opus",
+ "score": 0.305,
+ "pc1": -1.4278,
+ "pc2": 1.3519,
+ "pc3": 1.5736,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "b9ce8930",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": 0.2397,
+ "pc2": 1.4481,
+ "pc3": 0.5277,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "6c694ce9",
+ "model": "opus",
+ "score": 0.405,
+ "pc1": 0.2397,
+ "pc2": 1.4481,
+ "pc3": 0.5277,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "83b4415b",
+ "model": "opus",
+ "score": 0.895,
+ "pc1": 0.2397,
+ "pc2": 1.4481,
+ "pc3": 0.5277,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "37932d12",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -1.7536,
+ "pc2": 1.0849,
+ "pc3": 0.1646,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "b53d8e6f",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -1.7536,
+ "pc2": 1.0849,
+ "pc3": 0.1646,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "53a9f7eb",
+ "model": "opus",
+ "score": 0.28,
+ "pc1": -1.7536,
+ "pc2": 1.0849,
+ "pc3": 0.1646,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "71eeae15",
+ "model": "opus",
+ "score": 0.43,
+ "pc1": -1.6329,
+ "pc2": 1.2975,
+ "pc3": 1.8397,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "868a617f",
+ "model": "opus",
+ "score": 0.28,
+ "pc1": -1.6329,
+ "pc2": 1.2975,
+ "pc3": 1.8397,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "8c6cb19c",
+ "model": "opus",
+ "score": 0.805,
+ "pc1": -1.6329,
+ "pc2": 1.2975,
+ "pc3": 1.8397,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1",
+ "short_id": "68a6572f",
+ "model": "opus",
+ "score": 0.475,
+ "pc1": -1.6766,
+ "pc2": 1.1384,
+ "pc3": 0.9417,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2",
+ "short_id": "00b5cb8a",
+ "model": "opus",
+ "score": 0.365,
+ "pc1": -1.6766,
+ "pc2": 1.1384,
+ "pc3": 0.9417,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3",
+ "short_id": "e2cb7f2b",
+ "model": "opus",
+ "score": 0.865,
+ "pc1": -1.6766,
+ "pc2": 1.1384,
+ "pc3": 0.9417,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1",
+ "short_id": "4d465534",
+ "model": "opus",
+ "score": 0.765,
+ "pc1": -1.8407,
+ "pc2": 1.0914,
+ "pc3": 1.7618,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2",
+ "short_id": "330aae5e",
+ "model": "opus",
+ "score": 0.205,
+ "pc1": -1.8407,
+ "pc2": 1.0914,
+ "pc3": 1.7618,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3",
+ "short_id": "a59bd13b",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -1.8407,
+ "pc2": 1.0914,
+ "pc3": 1.7618,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1",
+ "short_id": "6c4adfb0",
+ "model": "opus",
+ "score": 0.865,
+ "pc1": -1.7324,
+ "pc2": 1.1266,
+ "pc3": -0.5233,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2",
+ "short_id": "e5199e69",
+ "model": "opus",
+ "score": 0.91,
+ "pc1": -1.7324,
+ "pc2": 1.1266,
+ "pc3": -0.5233,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3",
+ "short_id": "c049fcf5",
+ "model": "opus",
+ "score": 0.245,
+ "pc1": -1.7324,
+ "pc2": 1.1266,
+ "pc3": -0.5233,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "feb7d705",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -1.7407,
+ "pc2": 0.8602,
+ "pc3": 0.7559,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2",
+ "short_id": "3c9d94f5",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -1.7407,
+ "pc2": 0.8602,
+ "pc3": 0.7559,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3",
+ "short_id": "1a10ac67",
+ "model": "opus",
+ "score": 0.475,
+ "pc1": -1.7407,
+ "pc2": 0.8602,
+ "pc3": 0.7559,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "67153cc8",
+ "model": "opus",
+ "score": 0.315,
+ "pc1": -0.8827,
+ "pc2": 2.3936,
+ "pc3": 0.4307,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "cde3d475",
+ "model": "opus",
+ "score": 0.385,
+ "pc1": -0.8827,
+ "pc2": 2.3936,
+ "pc3": 0.4307,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "b7e96026",
+ "model": "opus",
+ "score": 0.88,
+ "pc1": -0.8827,
+ "pc2": 2.3936,
+ "pc3": 0.4307,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "886f5323",
+ "model": "opus",
+ "score": 0.49,
+ "pc1": 0.2359,
+ "pc2": 1.4922,
+ "pc3": 0.0903,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "d6549fa2",
+ "model": "opus",
+ "score": 0.825,
+ "pc1": 0.2359,
+ "pc2": 1.4922,
+ "pc3": 0.0903,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "6ccb77f1",
+ "model": "opus",
+ "score": 0.46,
+ "pc1": 0.2359,
+ "pc2": 1.4922,
+ "pc3": 0.0903,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "de9c4cc0",
+ "model": "sonnet",
+ "score": 0.155,
+ "pc1": -1.4177,
+ "pc2": 1.348,
+ "pc3": 1.5721,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "536bc021",
+ "model": "sonnet",
+ "score": 0.18,
+ "pc1": -1.4177,
+ "pc2": 1.348,
+ "pc3": 1.5721,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "92665abf",
+ "model": "sonnet",
+ "score": 0.715,
+ "pc1": -1.4177,
+ "pc2": 1.348,
+ "pc3": 1.5721,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "d2c1efc6",
+ "model": "sonnet",
+ "score": 0.305,
+ "pc1": 0.2498,
+ "pc2": 1.4441,
+ "pc3": 0.5262,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "b9741b31",
+ "model": "sonnet",
+ "score": 0.315,
+ "pc1": 0.2498,
+ "pc2": 1.4441,
+ "pc3": 0.5262,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "b683745c",
+ "model": "sonnet",
+ "score": 0.425,
+ "pc1": 0.2498,
+ "pc2": 1.4441,
+ "pc3": 0.5262,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "c13f247e",
+ "model": "sonnet",
+ "score": 0.49,
+ "pc1": -1.7436,
+ "pc2": 1.0809,
+ "pc3": 0.1631,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "0f0815e0",
+ "model": "sonnet",
+ "score": 0.475,
+ "pc1": -1.7436,
+ "pc2": 1.0809,
+ "pc3": 0.1631,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "f967cca3",
+ "model": "sonnet",
+ "score": 0.385,
+ "pc1": -1.7436,
+ "pc2": 1.0809,
+ "pc3": 0.1631,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "9378b63f",
+ "model": "sonnet",
+ "score": 0.76,
+ "pc1": -1.6228,
+ "pc2": 1.2935,
+ "pc3": 1.8382,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "63d07a83",
+ "model": "sonnet",
+ "score": 0.75,
+ "pc1": -1.6228,
+ "pc2": 1.2935,
+ "pc3": 1.8382,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "89f5d666",
+ "model": "sonnet",
+ "score": 0.255,
+ "pc1": -1.6228,
+ "pc2": 1.2935,
+ "pc3": 1.8382,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1",
+ "short_id": "222c497a",
+ "model": "sonnet",
+ "score": 0.44,
+ "pc1": -1.6665,
+ "pc2": 1.1344,
+ "pc3": 0.9402,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2",
+ "short_id": "a0b46dce",
+ "model": "sonnet",
+ "score": 0.72,
+ "pc1": -1.6665,
+ "pc2": 1.1344,
+ "pc3": 0.9402,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3",
+ "short_id": "9d5d71af",
+ "model": "sonnet",
+ "score": 0.41,
+ "pc1": -1.6665,
+ "pc2": 1.1344,
+ "pc3": 0.9402,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1",
+ "short_id": "3bbc243e",
+ "model": "sonnet",
+ "score": 0.365,
+ "pc1": -1.8306,
+ "pc2": 1.0874,
+ "pc3": 1.7603,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2",
+ "short_id": "ada76b96",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.8306,
+ "pc2": 1.0874,
+ "pc3": 1.7603,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3",
+ "short_id": "3ca73775",
+ "model": "sonnet",
+ "score": 0.495,
+ "pc1": -1.8306,
+ "pc2": 1.0874,
+ "pc3": 1.7603,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1",
+ "short_id": "225f2763",
+ "model": "sonnet",
+ "score": 0.33,
+ "pc1": -1.7224,
+ "pc2": 1.1226,
+ "pc3": -0.5248,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2",
+ "short_id": "0bee082b",
+ "model": "sonnet",
+ "score": 0.34,
+ "pc1": -1.7224,
+ "pc2": 1.1226,
+ "pc3": -0.5248,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3",
+ "short_id": "81d1772b",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.7224,
+ "pc2": 1.1226,
+ "pc3": -0.5248,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1",
+ "short_id": "f91e3319",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.7307,
+ "pc2": 0.8562,
+ "pc3": 0.7544,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2",
+ "short_id": "6a1b6728",
+ "model": "sonnet",
+ "score": 0.325,
+ "pc1": -1.7307,
+ "pc2": 0.8562,
+ "pc3": 0.7544,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3",
+ "short_id": "5a0dcfdc",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.7307,
+ "pc2": 0.8562,
+ "pc3": 0.7544,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "f333a385",
+ "model": "sonnet",
+ "score": 0.155,
+ "pc1": -0.8726,
+ "pc2": 2.3896,
+ "pc3": 0.4292,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "edfd3f04",
+ "model": "sonnet",
+ "score": 0.33,
+ "pc1": -0.8726,
+ "pc2": 2.3896,
+ "pc3": 0.4292,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "dec59666",
+ "model": "sonnet",
+ "score": 0.41,
+ "pc1": -0.8726,
+ "pc2": 2.3896,
+ "pc3": 0.4292,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "81d56cf5",
+ "model": "sonnet",
+ "score": 0.42,
+ "pc1": 1.3684,
+ "pc2": 0.5427,
+ "pc3": 0.1858,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "6a78fb22",
+ "model": "sonnet",
+ "score": 0.8,
+ "pc1": 0.246,
+ "pc2": 1.4882,
+ "pc3": 0.0888,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "4b3f7365",
+ "model": "sonnet",
+ "score": 0.315,
+ "pc1": 0.246,
+ "pc2": 1.4882,
+ "pc3": 0.0888,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "fa4f71b7",
+ "model": "sonnet",
+ "score": 0.355,
+ "pc1": 0.246,
+ "pc2": 1.4882,
+ "pc3": 0.0888,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "961a7131",
+ "model": "glm-4.5-air",
+ "score": 0.38,
+ "pc1": 4.025,
+ "pc2": -0.1249,
+ "pc3": -0.0671,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "299b6c41",
+ "model": "glm-4.7",
+ "score": 0.38,
+ "pc1": 4.0963,
+ "pc2": -0.1583,
+ "pc3": -0.109,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "0693e74d",
+ "model": "glm-4.7",
+ "score": 0.38,
+ "pc1": 4.0963,
+ "pc2": -0.1583,
+ "pc3": -0.109,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "255de2c3",
+ "model": "glm-4.7",
+ "score": 0.38,
+ "pc1": 4.0963,
+ "pc2": -0.1583,
+ "pc3": -0.109,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "a1c761c9",
+ "model": "glm-5.1",
+ "score": 0.38,
+ "pc1": 4.1606,
+ "pc2": -0.2347,
+ "pc3": 0.2316,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "c2541fee",
+ "model": "glm-5.1",
+ "score": 0.38,
+ "pc1": 4.1606,
+ "pc2": -0.2347,
+ "pc3": 0.2316,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "d61bbd6f",
+ "model": "glm-5.1",
+ "score": 0.305,
+ "pc1": 4.1606,
+ "pc2": -0.2347,
+ "pc3": 0.2316,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "7a348b81",
+ "model": "haiku",
+ "score": 0.485,
+ "pc1": -0.6094,
+ "pc2": 2.3977,
+ "pc3": 0.4716,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "8fe72fce",
+ "model": "haiku",
+ "score": 0.515,
+ "pc1": -0.6094,
+ "pc2": 2.3977,
+ "pc3": 0.4716,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "8932f117",
+ "model": "opus",
+ "score": 0.47,
+ "pc1": -0.3715,
+ "pc2": 2.9709,
+ "pc3": 0.79,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "52f8ab88",
+ "model": "opus",
+ "score": 0.5,
+ "pc1": -0.3715,
+ "pc2": 2.9709,
+ "pc3": 0.79,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "d6187c89",
+ "model": "opus",
+ "score": 0.5,
+ "pc1": -0.3715,
+ "pc2": 2.9709,
+ "pc3": 0.79,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "a1f49ced",
+ "model": "sonnet",
+ "score": 0.485,
+ "pc1": -0.3615,
+ "pc2": 2.9669,
+ "pc3": 0.7885,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "414139b2",
+ "model": "sonnet",
+ "score": 0.5,
+ "pc1": -0.3615,
+ "pc2": 2.9669,
+ "pc3": 0.7885,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=uns_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "ad21bf3b",
+ "model": "sonnet",
+ "score": 0.365,
+ "pc1": -0.3615,
+ "pc2": 2.9669,
+ "pc3": 0.7885,
+ "config_summary": "effort=high, prompt_style=simple, language=unspecified, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "ea686a12",
+ "model": "glm-4.5-air",
+ "score": 0.155,
+ "pc1": 2.9545,
+ "pc2": -1.552,
+ "pc3": -1.4776,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "fa02f9f7",
+ "model": "glm-4.5-air",
+ "score": 0.18,
+ "pc1": 2.9545,
+ "pc2": -1.552,
+ "pc3": -1.4776,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "7c1248e2",
+ "model": "glm-4.7",
+ "score": 0.315,
+ "pc1": 3.0258,
+ "pc2": -1.5855,
+ "pc3": -1.5195,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "c924670c",
+ "model": "glm-4.7",
+ "score": 0.305,
+ "pc1": 3.0258,
+ "pc2": -1.5855,
+ "pc3": -1.5195,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "187c67ef",
+ "model": "glm-5.1",
+ "score": 0.255,
+ "pc1": 3.0901,
+ "pc2": -1.6619,
+ "pc3": -1.179,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "5ca32e79",
+ "model": "glm-5.1",
+ "score": 0.155,
+ "pc1": 3.0901,
+ "pc2": -1.6619,
+ "pc3": -1.179,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "9d78ce6d",
+ "model": "glm-5.1",
+ "score": 0.37,
+ "pc1": 3.0901,
+ "pc2": -1.6619,
+ "pc3": -1.179,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run1",
+ "short_id": "0feabf41",
+ "model": "haiku",
+ "score": 0.47,
+ "pc1": -4.5399,
+ "pc2": -6.257,
+ "pc3": 3.1001,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run2",
+ "short_id": "4c7db3b9",
+ "model": "haiku",
+ "score": 0.485,
+ "pc1": -4.5399,
+ "pc2": -6.257,
+ "pc3": 3.1001,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=on_tread=off_twrite=on_web=off_run3",
+ "short_id": "40f9a902",
+ "model": "haiku",
+ "score": 0.79,
+ "pc1": -4.5399,
+ "pc2": -6.257,
+ "pc3": 3.1001,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "e2e04e75",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -1.6799,
+ "pc2": 0.9705,
+ "pc3": -0.939,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "b04257bc",
+ "model": "haiku",
+ "score": 0.28,
+ "pc1": -1.6799,
+ "pc2": 0.9705,
+ "pc3": -0.939,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "9b0e0479",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -1.6799,
+ "pc2": 0.9705,
+ "pc3": -0.939,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "daaf1998",
+ "model": "opus",
+ "score": 0.365,
+ "pc1": -1.442,
+ "pc2": 1.5437,
+ "pc3": -0.6206,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f3f3cd51",
+ "model": "opus",
+ "score": 0.755,
+ "pc1": -1.442,
+ "pc2": 1.5437,
+ "pc3": -0.6206,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "bdd519b4",
+ "model": "opus",
+ "score": 0.46,
+ "pc1": -1.442,
+ "pc2": 1.5437,
+ "pc3": -0.6206,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "92501938",
+ "model": "sonnet",
+ "score": 0.415,
+ "pc1": -1.432,
+ "pc2": 1.5397,
+ "pc3": -0.6221,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "12f4a113",
+ "model": "sonnet",
+ "score": 0.29,
+ "pc1": -1.432,
+ "pc2": 1.5397,
+ "pc3": -0.6221,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "6031abcf",
+ "model": "sonnet",
+ "score": 0.315,
+ "pc1": -1.432,
+ "pc2": 1.5397,
+ "pc3": -0.6221,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "d179f825",
+ "model": "glm-4.5-air",
+ "score": 0.18,
+ "pc1": 3.7242,
+ "pc2": 0.046,
+ "pc3": 0.2456,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "e128b57c",
+ "model": "glm-5.1",
+ "score": 0.34,
+ "pc1": 3.8598,
+ "pc2": -0.0639,
+ "pc3": 0.5442,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "025bcc22",
+ "model": "glm-5.1",
+ "score": 0.34,
+ "pc1": 3.8598,
+ "pc2": -0.0639,
+ "pc3": 0.5442,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "cd3f3c84",
+ "model": "glm-5.1",
+ "score": 0.34,
+ "pc1": 3.8598,
+ "pc2": -0.0639,
+ "pc3": 0.5442,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "7e61c670",
+ "model": "haiku",
+ "score": 0.715,
+ "pc1": -0.9102,
+ "pc2": 2.5685,
+ "pc3": 0.7842,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "6b33ee07",
+ "model": "haiku",
+ "score": 0.34,
+ "pc1": -0.9102,
+ "pc2": 2.5685,
+ "pc3": 0.7842,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "89be04d9",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -0.9102,
+ "pc2": 2.5685,
+ "pc3": 0.7842,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "59e8da6e",
+ "model": "opus",
+ "score": 0.39,
+ "pc1": -0.6723,
+ "pc2": 3.1417,
+ "pc3": 1.1026,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f501a861",
+ "model": "opus",
+ "score": 0.355,
+ "pc1": -0.6723,
+ "pc2": 3.1417,
+ "pc3": 1.1026,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "9720d53e",
+ "model": "opus",
+ "score": 0.75,
+ "pc1": -0.6723,
+ "pc2": 3.1417,
+ "pc3": 1.1026,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "5d88e9c7",
+ "model": "sonnet",
+ "score": 0.75,
+ "pc1": -0.6623,
+ "pc2": 3.1377,
+ "pc3": 1.1011,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "20dc3752",
+ "model": "sonnet",
+ "score": 0.74,
+ "pc1": -0.6623,
+ "pc2": 3.1377,
+ "pc3": 1.1011,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "4905874d",
+ "model": "sonnet",
+ "score": 0.75,
+ "pc1": -0.6623,
+ "pc2": 3.1377,
+ "pc3": 1.1011,
+ "config_summary": "effort=max, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run1",
+ "short_id": "1e3f4cdb",
+ "model": "haiku",
+ "score": 0.59,
+ "pc1": -4.6993,
+ "pc2": -6.1324,
+ "pc3": -0.7769,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run2",
+ "short_id": "c7b0bb6b",
+ "model": "haiku",
+ "score": 0.565,
+ "pc1": -4.6993,
+ "pc2": -6.1324,
+ "pc3": -0.7769,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3",
+ "short_id": "bbb70053",
+ "model": "haiku",
+ "score": 0.715,
+ "pc1": -4.6993,
+ "pc2": -6.1324,
+ "pc3": -0.7769,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "77966846",
+ "model": "haiku",
+ "score": 0.255,
+ "pc1": -2.7486,
+ "pc2": 1.0255,
+ "pc3": -5.5385,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "f6426aae",
+ "model": "haiku",
+ "score": 0.405,
+ "pc1": -2.7486,
+ "pc2": 1.0255,
+ "pc3": -5.5385,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "f86cae22",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -2.7486,
+ "pc2": 1.0255,
+ "pc3": -5.5385,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "b13700b7",
+ "model": "glm-4.5-air",
+ "score": 0.305,
+ "pc1": 2.5808,
+ "pc2": -1.3942,
+ "pc3": -2.9344,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "8d789027",
+ "model": "glm-4.7",
+ "score": 0.38,
+ "pc1": 2.6521,
+ "pc2": -1.4276,
+ "pc3": -2.9763,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "7fc5f846",
+ "model": "glm-5.1",
+ "score": 0.065,
+ "pc1": 2.7163,
+ "pc2": -1.5041,
+ "pc3": -2.6358,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "8bb02c7c",
+ "model": "haiku",
+ "score": 0.305,
+ "pc1": -2.0536,
+ "pc2": 1.1284,
+ "pc3": -2.3958,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "b1b1424a",
+ "model": "haiku",
+ "score": 0.225,
+ "pc1": -2.0536,
+ "pc2": 1.1284,
+ "pc3": -2.3958,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "d9899ed8",
+ "model": "haiku",
+ "score": 0.7,
+ "pc1": -2.0536,
+ "pc2": 1.1284,
+ "pc3": -2.3958,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "19d7fd45",
+ "model": "opus",
+ "score": 0.39,
+ "pc1": -1.8157,
+ "pc2": 1.7016,
+ "pc3": -2.0774,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "e10bfa92",
+ "model": "opus",
+ "score": 0.825,
+ "pc1": -1.8157,
+ "pc2": 1.7016,
+ "pc3": -2.0774,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=opus_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "b060d46a",
+ "model": "opus",
+ "score": 0.765,
+ "pc1": -1.8157,
+ "pc2": 1.7016,
+ "pc3": -2.0774,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+ "short_id": "7d8d44d6",
+ "model": "sonnet",
+ "score": 0.28,
+ "pc1": -1.8057,
+ "pc2": 1.6976,
+ "pc3": -2.0789,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+ "short_id": "837ded2f",
+ "model": "sonnet",
+ "score": 0.43,
+ "pc1": -1.8057,
+ "pc2": 1.6976,
+ "pc3": -2.0789,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+ "short_id": "f9d8871e",
+ "model": "sonnet",
+ "score": 0.315,
+ "pc1": -1.8057,
+ "pc2": 1.6976,
+ "pc3": -2.0789,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run1",
+ "short_id": "195c0c1f",
+ "model": "haiku",
+ "score": 0.65,
+ "pc1": -7.121,
+ "pc2": -7.5092,
+ "pc3": -0.2689,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run2",
+ "short_id": "18bcc1ad",
+ "model": "haiku",
+ "score": 0.47,
+ "pc1": -7.121,
+ "pc2": -7.5092,
+ "pc3": -0.2689,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=off_budget=low_model=haiku_pw=avail_prompt=detailed_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=off_tread=off_twrite=off_web=off_run3",
+ "short_id": "93e8feea",
+ "model": "haiku",
+ "score": 0.405,
+ "pc1": -7.121,
+ "pc2": -7.5092,
+ "pc3": -0.2689,
+ "config_summary": "effort=high, prompt_style=detailed, language=typescript, max_budget=low, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run1",
+ "short_id": "67825cfa",
+ "model": "haiku",
+ "score": 0.65,
+ "pc1": -4.7681,
+ "pc2": -4.8349,
+ "pc3": -7.8252,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run2",
+ "short_id": "ccc32a02",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -4.7681,
+ "pc2": -4.8349,
+ "pc3": -7.8252,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ },
+ {
+ "run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku_pw=off_prompt=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run3",
+ "short_id": "edcf7c7c",
+ "model": "haiku",
+ "score": 0.155,
+ "pc1": -4.7681,
+ "pc2": -4.8349,
+ "pc3": -7.8252,
+ "config_summary": "effort=high, prompt_style=simple, language=typescript, max_budget=high, strategy=use_subagents"
+ }
+ ],
+ "loadings": [
+ {
+ "feature": "model_glm-4.5-air",
+ "axis": "model",
+ "pc1": 0.0991,
+ "pc2": -0.0412,
+ "pc3": -0.0466
+ },
+ {
+ "feature": "model_glm-4.7",
+ "axis": "model",
+ "pc1": 0.1684,
+ "pc2": -0.0713,
+ "pc3": -0.0818
+ },
+ {
+ "feature": "model_glm-5.1",
+ "axis": "model",
+ "pc1": 0.2318,
+ "pc2": -0.1168,
+ "pc3": 0.0286
+ },
+ {
+ "feature": "model_haiku",
+ "axis": "model",
+ "pc1": -0.2062,
+ "pc2": -0.0912,
+ "pc3": -0.066
+ },
+ {
+ "feature": "model_opus",
+ "axis": "model",
+ "pc1": -0.0873,
+ "pc2": 0.1464,
+ "pc3": 0.0678
+ },
+ {
+ "feature": "model_sonnet",
+ "axis": "model",
+ "pc1": -0.0839,
+ "pc2": 0.1459,
+ "pc3": 0.0677
+ },
+ {
+ "feature": "effort_high",
+ "axis": "effort",
+ "pc1": -0.0228,
+ "pc2": -0.0811,
+ "pc3": -0.0728
+ },
+ {
+ "feature": "effort_max",
+ "axis": "effort",
+ "pc1": 0.0228,
+ "pc2": 0.0811,
+ "pc3": 0.0728
+ },
+ {
+ "feature": "prompt_style_detailed",
+ "axis": "prompt_style",
+ "pc1": -0.0799,
+ "pc2": -0.1528,
+ "pc3": 0.1676
+ },
+ {
+ "feature": "prompt_style_simple",
+ "axis": "prompt_style",
+ "pc1": 0.0799,
+ "pc2": 0.1528,
+ "pc3": -0.1676
+ },
+ {
+ "feature": "language_javascript",
+ "axis": "language",
+ "pc1": 0.0393,
+ "pc2": 0.0738,
+ "pc3": 0.0475
+ },
+ {
+ "feature": "language_typescript",
+ "axis": "language",
+ "pc1": -0.0749,
+ "pc2": -0.0982,
+ "pc3": -0.0618
+ },
+ {
+ "feature": "language_unspecified",
+ "axis": "language",
+ "pc1": 0.0631,
+ "pc2": 0.0612,
+ "pc3": 0.0375
+ },
+ {
+ "feature": "human_language_en",
+ "axis": "human_language",
+ "pc1": 0.082,
+ "pc2": 0.1246,
+ "pc3": 0.1542
+ },
+ {
+ "feature": "human_language_es",
+ "axis": "human_language",
+ "pc1": -0.082,
+ "pc2": -0.1246,
+ "pc3": -0.1542
+ },
+ {
+ "feature": "tool_read_off",
+ "axis": "tool_read",
+ "pc1": -0.1353,
+ "pc2": -0.1839,
+ "pc3": 0.188
+ },
+ {
+ "feature": "tool_read_on",
+ "axis": "tool_read",
+ "pc1": 0.1353,
+ "pc2": 0.1839,
+ "pc3": -0.188
+ },
+ {
+ "feature": "tool_write_off",
+ "axis": "tool_write",
+ "pc1": -0.1268,
+ "pc2": -0.1891,
+ "pc3": -0.1424
+ },
+ {
+ "feature": "tool_write_on",
+ "axis": "tool_write",
+ "pc1": 0.1268,
+ "pc2": 0.1891,
+ "pc3": 0.1424
+ },
+ {
+ "feature": "tool_edit_off",
+ "axis": "tool_edit",
+ "pc1": -0.1322,
+ "pc2": -0.1986,
+ "pc3": -0.0404
+ },
+ {
+ "feature": "tool_edit_on",
+ "axis": "tool_edit",
+ "pc1": 0.1322,
+ "pc2": 0.1986,
+ "pc3": 0.0404
+ },
+ {
+ "feature": "tool_glob_off",
+ "axis": "tool_glob",
+ "pc1": -0.1017,
+ "pc2": -0.1486,
+ "pc3": 0.191
+ },
+ {
+ "feature": "tool_glob_on",
+ "axis": "tool_glob",
+ "pc1": 0.1017,
+ "pc2": 0.1486,
+ "pc3": -0.191
+ },
+ {
+ "feature": "tool_grep_off",
+ "axis": "tool_grep",
+ "pc1": -0.1164,
+ "pc2": -0.1841,
+ "pc3": 0.0749
+ },
+ {
+ "feature": "tool_grep_on",
+ "axis": "tool_grep",
+ "pc1": 0.1164,
+ "pc2": 0.1841,
+ "pc3": -0.0749
+ },
+ {
+ "feature": "linter_off",
+ "axis": "linter",
+ "pc1": -0.0823,
+ "pc2": -0.2269,
+ "pc3": 0.1344
+ },
+ {
+ "feature": "linter_on",
+ "axis": "linter",
+ "pc1": 0.0823,
+ "pc2": 0.2269,
+ "pc3": -0.1344
+ },
+ {
+ "feature": "playwright_available",
+ "axis": "playwright",
+ "pc1": -0.2746,
+ "pc2": 0.2198,
+ "pc3": 0.0837
+ },
+ {
+ "feature": "playwright_instructed",
+ "axis": "playwright",
+ "pc1": 0.0335,
+ "pc2": -0.0037,
+ "pc3": -0.0115
+ },
+ {
+ "feature": "playwright_off",
+ "axis": "playwright",
+ "pc1": 0.2709,
+ "pc2": -0.2198,
+ "pc3": -0.0824
+ },
+ {
+ "feature": "context_file_none",
+ "axis": "context_file",
+ "pc1": 0.1343,
+ "pc2": 0.0996,
+ "pc3": 0.3611
+ },
+ {
+ "feature": "context_file_provided",
+ "axis": "context_file",
+ "pc1": -0.1343,
+ "pc2": -0.0996,
+ "pc3": -0.3611
+ },
+ {
+ "feature": "web_search_off",
+ "axis": "web_search",
+ "pc1": -0.1302,
+ "pc2": -0.2327,
+ "pc3": 0.0493
+ },
+ {
+ "feature": "web_search_on",
+ "axis": "web_search",
+ "pc1": 0.1302,
+ "pc2": 0.2327,
+ "pc3": -0.0493
+ },
+ {
+ "feature": "max_budget_high",
+ "axis": "max_budget",
+ "pc1": -0.09,
+ "pc2": -0.0133,
+ "pc3": -0.4068
+ },
+ {
+ "feature": "max_budget_low",
+ "axis": "max_budget",
+ "pc1": 0.09,
+ "pc2": 0.0133,
+ "pc3": 0.4068
+ },
+ {
+ "feature": "strategy_creative_validate",
+ "axis": "strategy",
+ "pc1": 0.0585,
+ "pc2": -0.006,
+ "pc3": -0.0354
+ },
+ {
+ "feature": "strategy_iterate",
+ "axis": "strategy",
+ "pc1": 0.0336,
+ "pc2": -0.0034,
+ "pc3": -0.0203
+ },
+ {
+ "feature": "strategy_none",
+ "axis": "strategy",
+ "pc1": 0.2684,
+ "pc2": -0.2323,
+ "pc3": 0.029
+ },
+ {
+ "feature": "strategy_use_subagents",
+ "axis": "strategy",
+ "pc1": -0.2837,
+ "pc2": 0.2327,
+ "pc3": -0.0187
+ },
+ {
+ "feature": "renderer_dom",
+ "axis": "renderer",
+ "pc1": 0.0858,
+ "pc2": -0.0237,
+ "pc3": -0.0234
+ },
+ {
+ "feature": "renderer_none",
+ "axis": "renderer",
+ "pc1": -0.0993,
+ "pc2": 0.0274,
+ "pc3": 0.0271
+ },
+ {
+ "feature": "renderer_webgl",
+ "axis": "renderer",
+ "pc1": 0.0493,
+ "pc2": -0.0136,
+ "pc3": -0.0134
+ },
+ {
+ "feature": "provider_anthropic",
+ "axis": "provider",
+ "pc1": -0.3425,
+ "pc2": 0.1598,
+ "pc3": 0.0513
+ },
+ {
+ "feature": "provider_zai",
+ "axis": "provider",
+ "pc1": 0.3425,
+ "pc2": -0.1598,
+ "pc3": -0.0513
+ }
+ ],
+ "axis_importance": [
+ {
+ "axis": "model",
+ "pc1": 0.8767,
+ "pc2": 0.6128,
+ "pc3": 0.3586,
+ "total": 1.8481
+ },
+ {
+ "axis": "strategy",
+ "pc1": 0.6442,
+ "pc2": 0.4745,
+ "pc3": 0.1033,
+ "total": 1.222
+ },
+ {
+ "axis": "playwright",
+ "pc1": 0.579,
+ "pc2": 0.4433,
+ "pc3": 0.1775,
+ "total": 1.1998
+ },
+ {
+ "axis": "context_file",
+ "pc1": 0.2687,
+ "pc2": 0.1993,
+ "pc3": 0.7223,
+ "total": 1.1903
+ },
+ {
+ "axis": "provider",
+ "pc1": 0.685,
+ "pc2": 0.3195,
+ "pc3": 0.1026,
+ "total": 1.1071
+ },
+ {
+ "axis": "max_budget",
+ "pc1": 0.1799,
+ "pc2": 0.0266,
+ "pc3": 0.8136,
+ "total": 1.0201
+ },
+ {
+ "axis": "tool_read",
+ "pc1": 0.2706,
+ "pc2": 0.3679,
+ "pc3": 0.376,
+ "total": 1.0145
+ },
+ {
+ "axis": "tool_write",
+ "pc1": 0.2536,
+ "pc2": 0.3782,
+ "pc3": 0.2848,
+ "total": 0.9166
+ },
+ {
+ "axis": "linter",
+ "pc1": 0.1645,
+ "pc2": 0.4538,
+ "pc3": 0.2688,
+ "total": 0.8871
+ },
+ {
+ "axis": "tool_glob",
+ "pc1": 0.2034,
+ "pc2": 0.2971,
+ "pc3": 0.3819,
+ "total": 0.8824
+ },
+ {
+ "axis": "web_search",
+ "pc1": 0.2604,
+ "pc2": 0.4654,
+ "pc3": 0.0987,
+ "total": 0.8245
+ },
+ {
+ "axis": "prompt_style",
+ "pc1": 0.1599,
+ "pc2": 0.3055,
+ "pc3": 0.3352,
+ "total": 0.8006
+ },
+ {
+ "axis": "tool_grep",
+ "pc1": 0.2329,
+ "pc2": 0.3681,
+ "pc3": 0.1499,
+ "total": 0.7509
+ },
+ {
+ "axis": "tool_edit",
+ "pc1": 0.2644,
+ "pc2": 0.3972,
+ "pc3": 0.0808,
+ "total": 0.7424
+ },
+ {
+ "axis": "human_language",
+ "pc1": 0.1641,
+ "pc2": 0.2493,
+ "pc3": 0.3083,
+ "total": 0.7217
+ },
+ {
+ "axis": "language",
+ "pc1": 0.1772,
+ "pc2": 0.2332,
+ "pc3": 0.1468,
+ "total": 0.5572
+ },
+ {
+ "axis": "renderer",
+ "pc1": 0.2344,
+ "pc2": 0.0647,
+ "pc3": 0.0639,
+ "total": 0.363
+ },
+ {
+ "axis": "effort",
+ "pc1": 0.0456,
+ "pc2": 0.1622,
+ "pc3": 0.1456,
+ "total": 0.3534
+ }
+ ]
+}
+\ No newline at end of file