Legal Research Bench Weighted Pass Immigration
Professional Work · 2026-06-23
Weighted-pass practice-area score for Immigration tasks in Vals AI Legal Research Bench.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 89.9 |
| Gemini 4 Carbon | 87.4 |
| Claude Opus 5 | 86.9 |
| Grok 4.6 | 85.4 |
| Muse Wonder Full | 85.3 |
| Grok 4.7 | 85.3 |
| GPT-6 Astra | 84.3 |
| Muse Spark 1.2 | 84.1 |
| Gemini 3.7 Flash | 83.8 |
| Mistral Large 4 Preview | 83.4 |
| Opus 4.7 | 83.2 |
| Claude Haiku 5.5 | 83.1 |
| Gemini 3.8 Flash | 82.9 |
| Muse Spark 1.1 | 82.5 |
| Grok 4.5 | 82.3 |
| GPT-5.5 | 82.1 |
| GLM-5.3 | 82.0 |
| Kimi K3 | 81.5 |
| Inkling | 81.3 |
| Muse Wonder | 81.2 |
| GPT-5.6 Sol | 81.2 |
| GLM-5.1 | 80.7 |
| GPT-5.6 Terra | 80.7 |
| DeepSeek V4 Pro 0813 | 80.7 |
| Ember-1 | 80.6 |
| Muse Spark 1.3 | 80.5 |
| Gemini 3.5 Flash | 80.2 |
| Gemini 3.6 Flash | 80.1 |
| Qwen3.8-Max | 79.4 |
| GPT-6.1 Sol | 79.2 |
| Sonnet 5 | 79.2 |
| DeepSeek V4.1 Flash 1017 | 79.0 |
| Qwen3.6 Plus (2026-04-02) | 78.8 |
| GPT-6 Luna | 78.6 |
| MiniMax M3 | 78.6 |
| GPT-5.6 Luna | 78.6 |
| GLM-5.3 Flash | 78.4 |
| Opus 4.8 | 78.3 |
| GLM-5.2 | 78.1 |
| Qwen3.8 27B | 78.0 |