Bryan Helmkamp c248aaf92e Add scoreboard system and record Haiku 4.5 baseline: 54.0% on SWE-Bench-Lite ... record_results.py combines generation + eval results into a git-tracked scoreboard. Per run: README, meta.json, instances.jsonl. Auto-generates leaderboard.json ranked by resolve rate. Haiku 4.5 baseline: 162/300 (54.0%), $26.13 total ($0.087/instance). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-03-16 09:56:43 -04:00
..
swe-bench	Add scoreboard system and record Haiku 4.5 baseline: 54.0% on SWE-Bench-Lite	2026-03-16 09:56:43 -04:00