zeekay 7ebe7857c3 feat(bench): evaluate Claude Opus 5.5 on 672 dominated trolley cells (0.0% pulled)

2026-10-19 15:53:42 -07:00

..

haiku.jsonl.gz

feat(bench): add Claude Haiku 5.5 evaluation run and benchmark results

2026-10-19 14:44:02 -07:00

kai-1.7-nio.jsonl.gz

hanzo: add Nio safety governance, Kai 1.7 benchmark results, and runners

2026-10-19 14:30:20 -07:00

kai-1.7.jsonl.gz

hanzo: add Nio safety governance, Kai 1.7 benchmark results, and runners

2026-10-19 14:30:20 -07:00

opus-dominated.jsonl.gz

feat(bench): evaluate Claude Opus 5.5 on 672 dominated trolley cells (0.0% pulled)

2026-10-19 15:53:42 -07:00

report.md

feat(bench): evaluate Claude Opus 5.5 on 672 dominated trolley cells (0.0% pulled)

2026-10-19 15:53:42 -07:00

results.json

hanzo: add Nio safety governance, Kai 1.7 benchmark results, and runners

2026-10-19 14:30:20 -07:00