Harvey's Legal Agent Benchmark - Corporate M&A
Professional Work · 2026-05-06
The Corporate M&A split of Harvey's Legal Agent Benchmark held-out evaluation. This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 20.0 |
| Claude Opus 5 | 20.0 |
| DeepSeek-V4-Pro | 20.0 |
| GLM-5.2 | 20.0 |
| Kimi K3 | 20.0 |
| Muse Spark 1.1 | 20.0 |
| Opus 4.8 | 0.0 |
| Sonnet 4.6 | 0.0 |
| Sonnet 5 | 0.0 |
| Gemini 3.5 Flash | 0.0 |
| Gemini 3.5 Flash-Lite | 0.0 |
| Gemini 3.6 Flash | 0.0 |
| GLM-5.1 | 0.0 |
| GPT-5.4 | 0.0 |
| GPT-5.5 | 0.0 |
| GPT-5.6 Luna | 0.0 |
| GPT-5.6 Sol | 0.0 |
| GPT-5.6 Terra | 0.0 |
| Grok 4.3 | 0.0 |
| Grok 4.5 | 0.0 |
| Inkling | 0.0 |
| Kimi K2.6 | 0.0 |
| Laguna M.1 | 0.0 |
| Laguna XS.2 | 0.0 |
| MiniMax M3 | 0.0 |
| Qwen3.7-Max | 0.0 |
| Qwen3.7-Plus | 0.0 |