Legal Research Bench Weighted Pass Constitutional/Civil Rights
Professional Work · 2026-06-23
Weighted-pass practice-area score for Constitutional/Civil Rights tasks in Vals AI Legal Research Bench.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Carbon | 91.2 |
| Muse Wonder Full | 90.7 |
| Gemini 4 Argon | 90.3 |
| Muse Wonder | 89.3 |
| Muse Spark Open | 89.2 |
| GLM-5.3 | 89.0 |
| GLM-5.3 Flash | 88.8 |
| Claude Opus 5 | 88.6 |
| GPT-5.6 Sol | 88.3 |
| Grok 4.6 | 88.2 |
| Gemini 3.8 Flash | 88.1 |
| Mistral Large 4 Preview | 88.1 |
| Sonnet 4.6 | 87.9 |
| Sonnet 5 | 87.0 |
| Opus 4.8 | 87.0 |
| DeepSeek V4.1 Flash 1017 | 86.6 |
| Ember-1 | 86.5 |
| GPT-5.6 Luna | 86.2 |
| Grok 4.7 | 86.1 |
| GLM-5.2 | 86.1 |
| Grok 4.5 | 85.9 |
| Step 5 Preview | 85.7 |
| DeepSeek-V4-Pro | 85.7 |
| DeepSeek V4.1 Flash | 85.7 |
| Muse Spark 1.1 | 85.6 |
| Gemini 3.5 Flash | 85.2 |
| Qwen3.8-Max | 85.2 |
| MiniMax M3 | 85.1 |
| Qwen3.8 Max (0902) | 85.0 |
| GLM-5.1 | 84.9 |
| Kimi K3 | 84.8 |
| DeepSeek-V4-Flash-0731 | 84.7 |
| DeepSeek V4 Pro 0813 | 84.7 |
| Muse Spark 1.2 | 84.7 |
| MiMo-V2.6-Pro | 84.3 |
| Hy4 Preview | 84.3 |
| Muse Spark 1.3 | 84.2 |
| Gemini 3.7 Flash | 84.1 |
| Opus 4.7 | 84.0 |
| GPT-6.1 Sol | 84.0 |