Spaces:
Running
Running
| title: Terminal-Bench 2.1, annotated | |
| emoji: 🔎 | |
| colorFrom: yellow | |
| colorTo: gray | |
| sdk: static | |
| pinned: false | |
| short_description: The TB2.1 leaderboard, trial by trial, with atif-scan review | |
| # Terminal-Bench 2.1, annotated | |
| The public [Terminal-Bench 2.1](https://hub.harborframework.com/) main leaderboard, re-read trial by | |
| trial with [atif-scan](https://github.com/evalstate/atif-scan). For every row: | |
| - **Highlights** — masked excerpts of where findings and benchmark-awareness stages happened; | |
| - **Trajectories** — atif-scan's static viewer of every finding-related step; | |
| - a task × attempt strip, review leads beside the leaderboard's own reward-hack rate, and a | |
| checks × rows matrix linking straight to the excerpts; | |
| - **data holes & accounting**: how much reasoning each row's traces hold (full, summary, hidden, | |
| unrecorded), compacted history, web results missing from the trace, unpaired tool results, and | |
| per-trial costs against the leaderboard's total. | |
| Findings are review leads, not verdicts. Leaderboard scores, reward-hack rates and costs are the | |
| leaderboard's own. Trace text is atif-scan's credential-masked export of public leaderboard trials. | |