AA-Briefcase — leaderboard
Metric: Rubric Pass Rate (%). Source: artificialanalysis.ai. 47 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3 | 50.97 |
| 2 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 42.32 |
| 3 | GPT-5.6 Sol (Max) | 41.85 |
| 4 | Grok 4.5 (High) | 40.71 |
| 5 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 39.34 |
| 6 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 38.69 |
| 7 | GLM-5.2 (Max) | 36.06 |
| 8 | GPT-5.5 (xHigh) | 33.44 |
| 9 | GPT-5.5 (High) | 30.61 |
| 10 | MiniMax-M3 | 30.3 |
| 11 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 28.92 |
| 12 | Gemini 3.5 Flash (High) | 27.73 |
| 13 | Gemini 3.5 Flash (Medium) | 27.64 |
| 14 | GPT-5.5 (Medium) | 26.57 |
| 15 | GLM-5.1 (Thinking) | 25.76 |
Interactive version: aibenchmarks.dev/benchmark?slug=aa-briefcase · How the rankings work · Data refreshed daily, snapshot 2026-07-22.