Legal Research Bench Weighted Pass Family
Professional Work · 2026-06-23
Weighted-pass practice-area score for Family tasks in Vals AI Legal Research Bench.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 86.6 |
| Gemini 4 Carbon | 84.8 |
| Muse Spark 1.3 | 84.3 |
| Muse Wonder | 83.4 |
| Muse Wonder Full | 83.0 |
| Gemini 4 Argon | 81.5 |
| Grok 4.6 | 80.4 |
| GPT-5.6 Terra | 79.3 |
| GPT-5.6 Luna | 78.4 |
| GLM-5.3 Flash | 78.1 |
| DeepSeek V4.1 Flash | 77.7 |
| GLM-5.3 | 77.6 |
| Grok 4.7 | 77.5 |
| MiMo-V2.6-Pro | 77.4 |
| Opus 4.8 | 77.3 |
| GPT-6 Astra | 77.3 |
| DeepSeek V4 Pro 0813 | 77.3 |
| Sonnet 4.6 | 76.8 |
| GPT-5.6 Sol | 76.7 |
| Qwen3.8 Max (0902) | 76.4 |
| Mistral Large 4 Preview | 76.4 |
| Opus 4.7 | 76.3 |
| Qwen3.8-Max | 75.4 |
| Ember-1 | 75.4 |
| Hy4 Preview | 75.2 |
| Gemini 3.8 Flash | 75.0 |
| Gemini 3.5 Flash | 74.9 |
| Muse Spark 1.2 | 74.5 |
| DeepSeek-V4-Flash-0731 | 74.3 |
| DeepSeek V4.1 Flash 1017 | 74.2 |
| Claude Haiku 5.5 | 74.1 |
| Muse Spark 1.1 | 73.7 |
| GPT-6.1 Sol | 73.4 |
| Muse Spark Open | 72.8 |
| Kimi K3 | 72.4 |
| Sonnet 5 | 72.2 |
| Inkling | 71.7 |
| GPT-6 Luna | 71.5 |
| MiniMax M3.1 Flash | 71.4 |
| MiMo-V2.6-Flash | 70.9 |