Legal Research Bench Health
Professional Work · 2026-06-23
This row reports the practice-area score for Health tasks in Vals AI Legal Research Bench.
Top models (higher is better)
| Model | Score |
|---|---|
| Ember-1 | 80.0 |
| GPT-5.6 Sol | 80.0 |
| GPT-5.6 Terra | 80.0 |
| Claude Opus 5 | 76.7 |
| Gemini 4 Argon | 76.7 |
| GLM-5.3 | 76.7 |
| GPT-6.1 Sol | 76.7 |
| GPT-6 Astra | 76.7 |
| Grok 4.7 | 76.7 |
| Kimi K3 | 76.7 |
| Muse Wonder | 76.7 |
| DeepSeek V4.1 Flash | 73.3 |
| GLM-5.3 Flash | 73.3 |
| Grok 4.6 | 73.3 |
| Kimi K3.1 Pro | 73.3 |
| Muse Spark 1.3 | 73.3 |
| Qwen3.8-Max | 73.3 |
| Gemini 4 Carbon | 70.0 |
| GPT-5.6 Luna | 70.0 |
| MiMo-V2.6-Pro | 70.0 |
| Claude Haiku 5.5 | 66.7 |
| DeepSeek V4.1 Flash 1017 | 66.7 |
| GPT-5.5 | 66.7 |
| Grok 4.5 | 66.7 |
| Hy4 Preview | 66.7 |
| Muse Wonder Full | 66.7 |
| Sonnet 5 | 63.3 |
| Qwen3.8 27B | 63.3 |
| DeepSeek V4 Pro 0813 | 60.0 |
| GPT-6 Sol | 60.0 |
| Gemini 3.8 Flash | 56.7 |
| GPT-6.1 Terra | 56.7 |
| Muse Spark 1.2 | 56.7 |
| Qwen3.8 Max (0902) | 56.7 |
| Opus 4.7 | 53.3 |
| Opus 4.8 | 53.3 |
| Sonnet 4.6 | 53.3 |
| GPT-6 Luna | 53.3 |
| MiMo-V2.6-Flash | 53.3 |
| Muse Spark Open | 53.3 |