Legal Research Bench Weighted Pass Health
Professional Work · 2026-06-23
Weighted-pass practice-area score for Health tasks in Vals AI Legal Research Bench.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 97.5 |
| Claude Opus 5 | 96.8 |
| Gemini 4 Carbon | 96.8 |
| Grok 4.6 | 96.7 |
| Muse Wonder | 96.5 |
| Ember-1 | 96.2 |
| DeepSeek V4.1 Flash 1017 | 96.2 |
| Qwen3.8-Max | 96.2 |
| Gemini 4 Argon | 96.0 |
| Muse Wonder Full | 95.8 |
| Grok 4.7 | 95.5 |
| GPT-6.1 Sol | 95.5 |
| Hy4 Preview | 95.5 |
| GLM-5.3 | 95.2 |
| MiMo-V2.6-Pro | 94.9 |
| DeepSeek V4.1 Flash | 94.9 |
| GPT-6 Astra | 94.8 |
| Kimi K3 | 94.6 |
| Muse Spark 1.3 | 94.6 |
| Claude Haiku 5.5 | 94.5 |
| Qwen3.8 27B | 94.3 |
| GPT-5.6 Luna | 93.8 |
| Gemini 3.8 Flash | 93.8 |
| GPT-5.5 | 93.6 |
| Grok 4.5 | 93.2 |
| GPT-5.6 Terra | 93.2 |
| GLM-5.3 Flash | 92.9 |
| Muse Spark 1.2 | 92.9 |
| GPT-6.1 Terra | 92.8 |
| Mistral Large 4 Preview | 92.4 |
| MiniMax M3 | 92.2 |
| Sonnet 5 | 92.1 |
| GPT-6 Sol | 91.7 |
| Gemini 3.5 Flash | 91.5 |
| GLM-5.2 | 91.3 |
| DeepSeek-V4-Pro | 91.2 |
| GPT-6 Luna | 91.1 |
| Opus 4.8 | 90.8 |
| Muse Spark Open | 90.8 |
| Gemini 3.7 Flash | 90.5 |