← Benchmarks
AA-Briefcase v1.1
AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.
id aa-briefcase-1.1 · max 3000 · 2 models reported
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 Anthropic | 1822.00 |
| 2 | Grok 4.7 xAI | 1657.00 |