Legal Research Bench Weighted Pass Business/Commercial
Professional Work · 2026-06-23
Weighted-pass practice-area score for Business/Commercial tasks in Vals AI Legal Research Bench.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 92.2 |
| Gemini 4 Argon | 91.9 |
| GLM-5.3 Flash | 91.3 |
| Gemini 3.8 Flash | 91.1 |
| Gemini 4 Carbon | 91.0 |
| Muse Wonder Full | 89.8 |
| Grok 4.6 | 89.8 |
| Gemini 3.7 Flash | 89.5 |
| Muse Spark 1.2 | 89.2 |
| Muse Spark 1.1 | 89.1 |
| Step 5 Preview | 89.1 |
| GLM-5.3 | 89.1 |
| GPT-5.6 Sol | 89.0 |
| Muse Spark Open | 89.0 |
| Muse Spark 1.3 | 88.7 |
| Opus 4.7 | 88.3 |
| Sonnet 4.6 | 88.0 |
| DeepSeek V4.1 Flash 1017 | 87.8 |
| Hy4 Preview | 87.7 |
| MiniMax M3.1 Flash | 87.6 |
| Ember-1 | 87.6 |
| GLM-5.2 | 87.5 |
| Grok 4.7 | 87.4 |
| GPT-5.6 Luna | 87.3 |
| Claude Haiku 5.5 | 87.0 |
| Muse Wonder | 86.9 |
| Grok 4.5 | 86.8 |
| GPT-5.5 | 86.8 |
| Sonnet 5 | 86.8 |
| Qwen3.8 27B | 86.8 |
| DeepSeek V4.1 Flash | 86.7 |
| Qwen3.8-Max | 86.7 |
| DeepSeek-V4-Pro | 86.5 |
| GPT-5.6 Terra | 86.1 |
| Opus 4.8 | 86.1 |
| Mistral Large 4 Preview | 86.0 |
| MiMo-V2.6-Pro | 85.0 |
| Gemini 3.6 Flash | 84.6 |
| GPT-6.1 Sol | 84.2 |
| Gemini 3.5 Flash | 84.1 |