Computer Anthology Terminal Tasks (Claude Code): leaderboard
Vetto's Computer Anthology Terminal Tasks v1.0 run under the Claude Code agent scaffold — 100 held-out terminal jobs graded by per-task sandboxed verifiers; pass@1 over 5 trials per task. Reported per model+scaffold pair because the scaffold moves the score substantially.
Metric: pass@1 (%). Source: vetto.ai. Saturation forecast: Around November 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (High) | 55.2 | #10 (Claude Fable 5.1) |
| 2 | Claude Opus 5 (High) | 54 | #16 (Claude Opus 5) |
| 3 | Claude Fable 5 (High) | 54 | #20 (Claude Fable 5) |
| 4 | Claude Opus 4.8 (High) | 38 | #39 (Claude Opus 4.8) |
| 5 | Claude Sonnet 5 (High) | 25.6 | #65 (Claude Sonnet 5) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=computer-anthology-terminal-tasks-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-05.