TestsBenchmarks · Agentic
Vals Legal Research Bench
Agentic legal research tasks across US law areas, graded on correctness of the research answer.
% solvedHigher is betterCounts toward:Weights: Research & analysis ×0.8The test's websiteOfficial page ↗
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 55.3% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 2 | Claude Opus 5 | Anthropic | 55.3% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 3 | Claude Fable 5.1 | Anthropic | 55.3% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 4 | Gemini 4 Argon | Google (Gemini / DeepMind) | 54.8% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 5 | Claude Opus 5.5 | Anthropic | 50.5% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 6 | Claude Fable 5 | Anthropic | 49.5% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 7 | GLM-5.3 | Z.ai (Zhipu) | 49.0% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 8 | Grok 4.6 | SpaceXAI (formerly xAI) | 48.1% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 9 | GPT-5.6 Sol | OpenAI | 48.1% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 10 | Claude Sonnet 5.5 | Anthropic | 48.1% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 11 | Qwen3.8 Max (0803) | Qwen (Alibaba) | 47.6% | Defaultvals id alibaba/qwen3.8-max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 12 | Grok 4.7 | SpaceXAI (formerly xAI) | 47.1% | Extra highreasoning_effort=xhigh | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 13 | MiMo-V2.6-Pro | Xiaomi MiMo | 47.1% | Defaultvals id xiaomi/mimo-v2.6-pro | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 14 | GLM-5.3-Flash | Z.ai (Zhipu) | 45.2% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 15 | Hy4 preview | Tencent Hunyuan | 45.2% | Defaultvals id tencent/hy4-preview | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 16 | Ember-1 | Fireworks AI | 44.7% | Defaultvals id fireworks/ember-1 | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 17 | Kimi K3 | Moonshot AI (Kimi) | 44.2% | Defaultvals id kimi/kimi-k3 | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 18 | Muse Spark 1.2 | Meta (Meta Superintelligence Labs, Muse) | 43.8% | Extra highreasoning_effort=xhigh | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 19 | Claude Opus 4.8 | Anthropic | 43.8% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 20 | Claude Sonnet 5 | Anthropic | 41.8% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 21 | DeepSeek V4.1 Flash | DeepSeek | 41.3% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 22 | DeepSeek V4 Pro (0813) | DeepSeek | 40.9% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 23 | GPT-6 Astra | OpenAI | 39.4% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 24 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 38.9% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 25 | GPT-6.1 Sol | OpenAI | 38.5% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 26 | Qwen3.8 27B | Qwen (Alibaba) | 36.1% | Extra highreasoning_effort=xhigh | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 27 | DeepSeek V4 Flash (0731) | DeepSeek | 30.3% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 28 | GPT-6 Luna | OpenAI | 30.3% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 29 | GPT-6 Sol | OpenAI | 28.8% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 30 | DeepSeek V4 Pro (Preview, 0423) | DeepSeek | 23.1% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |