Legal Research Bench leaderboard
Agentic US legal research: finding and applying the authority that answers a question. Muse Spark 1.3 Max leads with 55.29%.
- Models
- 82
- Leader
- Muse Spark 1.3 Max
- Source
- Vals AI
- As of
- Oct 24, 2026
Open weightsProprietaryBest for the price
Full leaderboard
| Rank | Model | Lab | Accuracy | Cost / test | Harness | Price in / out |
|---|---|---|---|---|---|---|
| 1 | Muse Spark 1.3 Max | Meta | 55.29% | $0.59 | — | — |
| 2 | Claude Opus 5 | Anthropic | 55.29% | $6.76 | — | $5 / $25 |
| 3 | Claude Fable 5.1 | Anthropic | 55.29% | $23.06 | — | $10 / $50 |
| 4 | Gemini 4 Argon | 54.81% | $6.45 | — | $2 / $10 | |
| 5 | Muse Wonder Full | Meta | 53.37% | $3.60 | — | — |
| 6 | Muse Wonder | Meta | 50.48% | $3.98 | — | $4 / $20 |
| 7 | Claude Opus 5.5 | Anthropic | 50.48% | $25.16 | — | $4 / $20 |
| 8 | Claude Fable 5 | Anthropic | 49.52% | $9.79 | — | $10 / $50 |
| 9 | GLM-5.3 | Z.ai | 49.04% | $2.24 | — | $0.079 / $1.40 |
| 10 | Grok 4.6 | xAI | 48.08% | $1.53 | — | $2 / $6 |
| 11 | GPT-5.6 Sol | OpenAI | 48.08% | $21.61 | — | $4 / $20 |
| 12 | Claude Sonnet 5.5 | Anthropic | 48.08% | $14.83 | — | $2 / $10 |
| 14 | Grok 4.7 | xAI | 47.12% | $4.92 | — | $2 / $6 |
| 15 | MiMo-V2.6-Pro | Xiaomi | 47.12% | $0.18 | — | $0.43 / $0.87 |
| 16 | Kimi K3 | Moonshot AI | 46.15% | $3.47 | — | $0.24 / $11 |
| 17 | Qwen3.8-Max | Alibaba | 46.15% | $5.31 | — | $2 / $6 |
| 19 | GLM-5.3-Flash | Z.ai | 45.19% | $0.12 | — | $0.15 / $0.50 |
| 20 | Hy4 preview | Tencent | 45.19% | $0.85 | — | $0.75 / $2.25 |
| 21 | EEmber-1 | Fireworks AI | 44.71% | $3.67 | — | $3 / $15 |
| 22 | Muse Spark 1.2 | Meta | 43.75% | $0.51 | — | $1.25 / $4.25 |
| 23 | Claude Opus 4.8 | Anthropic | 43.75% | $2.82 | — | $5 / $25 |
| 24 | Claude Haiku 5.5 | Anthropic | 43.27% | $1.63 | — | $0.10 / $0.50 |
| 25 | Claude Sonnet 5 | Anthropic | 41.83% | $2.72 | — | $2 / $10 |
| 26 | GLM Legal | Z.ai | 41.83% | $0.05 | — | — |
| 27 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 41.35% | $0.25 | — | $0.15 / $0.60 |
| 28 | GPT-5.6 Terra | OpenAI | 41.35% | $7.91 | — | $2 / $12 |
| 29 | Muse Spark 1.3 | Meta | 40.87% | $0.65 | — | $1.25 / $4.25 |
| 31 | Step 5 Preview | StepFun | 40.38% | $0.84 | — | $1 / $2.70 |
| 32 | GPT-5.5 | OpenAI | 40.38% | $7.40 | — | $5 / $30 |
| 33 | GPT-6 Astra | OpenAI | 39.42% | $10.58 | — | $10 / $50 |
| 34 | Gemini 3.8 Flash | 38.94% | $1.63 | — | $0.82 / $4.13 | |
| 35 | Claude Opus 4.7 | Anthropic | 38.46% | $3.06 | — | $5 / $25 |
| 36 | Claude Sonnet 4.6 | Anthropic | 38.46% | $2.30 | — | $3 / $15 |
| 37 | Muse Spark Open | Meta | 38.46% | $1.56 | — | $1.25 / $4.25 |
| 38 | GPT-6.1 Sol | OpenAI | 38.46% | $3.38 | — | $2 / $10 |
| 39 | Muse Spark 1.1 | Meta | 37.98% | $0.38 | — | $1.25 / $4.25 |
| 40 | MiMo-V2.6-Flash | Xiaomi | 37.98% | $0.07 | — | $0.14 / $0.28 |
| 41 | Grok 4.5 | xAI | 37.98% | $1.09 | — | $2 / $6 |
| 42 | Kimi K3.1 Pro | Moonshot AI | 37.50% | $7.23 | — | $2 / $10 |
| 43 | GPT-5.6 Luna | OpenAI | 36.54% | $0.85 | — | $0.20 / $1.20 |
| 44 | Qwen3.8-27B | Alibaba | 36.06% | $2.16 | — | $0.20 / $2.50 |
| 45 | Gemini 3.7 Flash | 34.62% | $0.76 | — | $0.75 / $3.75 | |
| 46 | MiniMax-M3.1-Flash | MiniMax | 34.13% | $0.44 | — | $0.15 / $0.60 |
| 47 | Mistral Large 4 | Mistral AI | 31.73% | $5.33 | — | $1.36 / $4.18 |
| 48 | GLM-5.2 | Z.ai | 31.25% | $0.89 | — | $0.034 / $7 |
| 49 | Gemini 3.5 Flash | 30.77% | $1.31 | — | $1.50 / $9 | |
| 50 | DeepSeek-V4-Flash | DeepSeek | 30.29% | $0.28 | — | $0.042 / $0.18 |
| 51 | GPT-6 Luna | OpenAI | 30.29% | $0.44 | — | $0.10 / $0.50 |
| 52 | MiniMax-M3 | MiniMax | 29.81% | $0.34 | — | $0.30 / $1.20 |
| 53 | BBeam 1.0 | Reflection AI | 28.85% | N/A | — | — |
| 54 | Mercury 3 | Inception | 28.85% | $0.07 | — | $0.10 / $0.35 |
| 55 | GPT-6 Sol | OpenAI | 28.85% | $4.90 | — | $2 / $10 |
| 56 | IInkling | Thinky | 28.36% | $0.49 | — | $1 / $4.05 |
| 57 | GLM-5.1 | Z.ai | 27.89% | $0.39 | — | $1.40 / $4.40 |
| 58 | IInkling-Small | Thinky | 25.48% | $0.14 | — | $0.45 / $1.20 |
| 59 | Qwen3.7-Max-Preview | Alibaba | 25.48% | $1.40 | — | $1.48 / $4.42 |
| 60 | Gemini 3.6 Flash | 25.00% | $0.47 | — | $0.75 / $3.75 | |
| 61 | DeepSeek-V4-Pro | DeepSeek | 23.08% | $0.68 | — | $0.66 / $1.98 |
| 62 | Gemini 3.1 Pro Preview | 20.67% | $1.10 | — | $2 / $12 | |
| 63 | Gemini 3 Flash | 18.27% | $0.14 | — | $0.50 / $3 | |
| 64 | Qwen3.7-Plus | Alibaba | 16.35% | $0.30 | — | $0.32 / $1.28 |
| 65 | MiMo-V2.5-Pro | Xiaomi | 15.87% | $0.08 | — | $0.30 / $0.61 |
| 66 | Kimi K2.5 | Moonshot AI | 15.87% | $0.23 | — | $0.50 / $2.50 |
| 67 | Kimi K2.6 | Moonshot AI | 15.87% | $1.52 | — | $0.65 / $3.41 |
| 68 | Grok 4.3 | xAI | 15.38% | $0.20 | — | $1.25 / $2.50 |
| 69 | LLing 3.0 Flash Fin | — | 15.38% | $0.03 | — | — |
| 70 | Nemotron 3 Ultra | NVIDIA | 15.38% | N/A | — | $0.60 / $2.40 |
| 71 | Qwen3.6-Plus | Alibaba | 14.90% | $0.70 | — | $0.33 / $1.95 |
| 72 | Gemini 3.5 Flash-Lite | 13.94% | $0.12 | — | $0.30 / $2.50 | |
| 73 | Grok 4.20 | xAI | 13.94% | $0.26 | — | $1.25 / $2.50 |
| 74 | GPT-5.4 mini | OpenAI | 12.50% | $1.86 | — | $0.75 / $4.50 |
| 75 | Claude Haiku 4.5 | Anthropic | 10.58% | $0.27 | — | $1 / $5 |
| 76 | MiniMax-M2.7 | MiniMax | 10.58% | $0.22 | — | $0.30 / $1.20 |
| 77 | MiMo-V2.5 | Xiaomi | 9.13% | $0.03 | — | $0.12 / $0.24 |
| 78 | Mistral Medium 3.5 | Mistral AI | 9.13% | $1.31 | — | $1.50 / $7.50 |
| 79 | GPT-5.4 nano | OpenAI | 6.25% | $0.14 | — | $0.20 / $1.25 |
| 80 | Mercury 2.5 | Inception | 4.33% | $0.06 | — | $0.04 / $0.15 |
| 81 | Gemini 3.1 Flash-Lite Preview | 3.37% | $0.01 | — | $0.25 / $1.50 | |
| 82 | Nemotron 3.5 Lightning | Fireworks AI | 2.88% | $0.00 | — | $0.07 / $0.20 |
| 83 | LLaguna M.1 | Poolside | 2.40% | N/A | — | — |
| 84 | LLaguna XS.2 | Poolside | 0.96% | N/A | — | — |
| 85 | LLing 3.0 Flash | inclusionAI | 0.00% | $0.04 | — | $0.021 / $0.063 |
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview


