hanzoai/trolley-bench
2
0
Fork 0
mirror of https://github.com/hanzoai/trolley-bench.git synced 2026-10-30 15:00:49 +00:00
Code Issues Packages Projects Releases Wiki Activity
9 Commits 5 Branches 0 Tags

Default Branch

main

7ebe7857c3 · feat(bench): evaluate Claude Opus 5.5 on 672 dominated trolley cells (0.0% pulled) · Updated 2026-10-19 22:53:42 +00:00
 ZIP  TAR.GZ

Branches

hanzo/readme-like-for-like-comparison-218a

8dd883c2f4 · README: like-for-like comparison and corrected headline numbers · Updated 2026-10-29 01:12:07 +00:00    hanzoai

0
1
 ZIP  TAR.GZ
fm/trolley-bench-repro-readme

c205b79149 · docs(readme): lead reproduction verdict with findings · Updated 2026-10-15 05:50:49 +00:00    hanzoai

5
2
 ZIP  TAR.GZ
fm/trolley-bench-draft-markers

6586ae76af · chore: remove private publication markers · Updated 2026-10-15 01:33:18 +00:00    hanzoai

6
1
 ZIP  TAR.GZ
fm/trolley-bench-latest

26576dfdef · feat: add v2 benchmark and registered reproduction sample · Updated 2026-10-14 22:02:40 +00:00    hanzoai

7
1
 ZIP  TAR.GZ