loop-benchmarking

Controlled experiments across agentic coding configurations. Same task, one variable, what actually works.
git clone https://git.shiptheloop.com/loop-benchmarking.git
Log | Files | Refs | README

commit 99e78c4a88da398f355eb9f714bbb71fb0a7e0dd
parent f8ffb79af032ef659f675c9670f6d83092244df1
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Sun,  5 Apr 2026 08:48:31 +0200

Fix model order: haiku, sonnet, opus

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Diffstat:
Mdashboard/src/components/Variability.tsx | 2+-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dashboard/src/components/Variability.tsx b/dashboard/src/components/Variability.tsx @@ -59,7 +59,7 @@ interface BoxPlotStats { } function computeBoxPlots(cells: Cell[]): BoxPlotStats[] { - const MODEL_ORDER: Record<string, number> = { haiku: 1, opus: 2, sonnet: 3 }; + const MODEL_ORDER: Record<string, number> = { haiku: 1, sonnet: 2, opus: 3 }; const models = Array.from(new Set(cells.map((c) => c.meta.model))) .sort((a, b) => (MODEL_ORDER[a] || 99) - (MODEL_ORDER[b] || 99)); const results: BoxPlotStats[] = [];

Impressum · Datenschutz