Harvey LAB-AA - Corporate Governance: leaderboard
Metric: Criterion Pass Rate (%). Source: artificialanalysis.ai. 43 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Muse Spark 1.3 (xHigh) | 95.89 |
| 2 | Kimi K3 (Max) | 95.21 |
| 3 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 92.81 |
| 4 | GLM-5.2 (Max) | 92.47 |
| 5 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 92.12 |
| 6 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 91.78 |
| 7 | MiniMax-M3 | 91.44 |
| 8 | Grok 4.5 (High) | 91.44 |
| 9 | Kimi K2.6 | 90.41 |
| 10 | GPT-5.6 Luna (Max) | 89.73 |
| 11 | Gemini 3.7 Flash (High) | 88.7 |
| 12 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 88.01 |
| 13 | Kimi K2.7 Code | 86.3 |
| 14 | Qwen 3.7 Max | 85.62 |
| 15 | GPT-5.5 (xHigh) | 85.62 |
Interactive version: theaggregate.ai/benchmark?slug=harvey-lab-aa-corporate-governance · How It Works · Data refreshed daily, snapshot 2026-09-19.