Legal Index leaderboard
Vals AI’s composite of legal tasks: case law, legal reasoning and legal research. Muse Wonder Full leads with 77.86%.
- Models
- 28
- Leader
- Muse Wonder Full
- 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 Wonder Full | Meta | 77.86% | $3.72 | — | — |
| 2 | Gemini 4 Argon | 76.72% | $6.82 | — | $2 / $10 | |
| 3 | Muse Wonder | Meta | 75.26% | $4.32 | — | $4 / $20 |
| 4 | GLM-5.3 | Z.ai | 74.58% | $2.68 | — | $0.079 / $1.40 |
| 5 | Qwen3.8-Max | Alibaba | 73.90% | $4.25 | — | $2 / $6 |
| 6 | Grok 4.7 | xAI | 72.60% | $5.82 | — | $2 / $6 |
| 7 | Claude Opus 5.5 | Anthropic | 72.33% | $20.54 | — | $4 / $20 |
| 8 | MiMo-V2.6-Pro | Xiaomi | 72.14% | $0.18 | — | $0.43 / $0.87 |
| 9 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 71.86% | $0.59 | — | $0.15 / $0.60 |
| 10 | Kimi K3 | Moonshot AI | 71.72% | $3.47 | — | $0.24 / $11 |
| 11 | Hy4 preview | Tencent | 71.70% | $0.81 | — | $0.75 / $2.25 |
| 12 | GLM-5.3-Flash | Z.ai | 71.05% | $0.19 | — | $0.15 / $0.50 |
| 13 | Claude Haiku 5.5 | Anthropic | 70.27% | $2.35 | — | $0.10 / $0.50 |
| 14 | Gemini 3.8 Flash | 69.78% | $2.05 | — | $0.82 / $4.13 | |
| 15 | DeepSeek-V4-Pro | DeepSeek | 69.01% | $0.87 | — | $0.66 / $1.98 |
| 16 | MiMo-V2.6-Flash | Xiaomi | 68.99% | $0.07 | — | $0.14 / $0.28 |
| 17 | GPT-6.1 Sol | OpenAI | 68.72% | $2.75 | — | $2 / $10 |
| 18 | Muse Spark Open | Meta | 68.51% | $5.36 | — | $1.25 / $4.25 |
| 19 | GPT-6 Astra | OpenAI | 68.39% | $13.94 | — | $10 / $50 |
| 20 | Claude Sonnet 5.5 | Anthropic | 68.02% | $13.56 | — | $2 / $10 |
| 21 | MiniMax-M3.1-Flash | MiniMax | 67.07% | $0.41 | — | $0.15 / $0.60 |
| 22 | Kimi K3.1 Pro | Moonshot AI | 67.04% | $6.63 | — | $2 / $10 |
| 23 | Mistral Large 4 | Mistral AI | 65.61% | $4.08 | — | $1.36 / $4.18 |
| 24 | Mercury 3 | Inception | 62.96% | $0.10 | — | $0.10 / $0.35 |
| 25 | GPT-6 Luna | OpenAI | 62.20% | $0.31 | — | $0.10 / $0.50 |
| 26 | BBeam 1.0 | Reflection AI | 61.80% | N/A | — | — |
| 27 | IInkling-Small | Thinky | 57.83% | $0.14 | — | $0.45 / $1.20 |
| 28 | IInkling | Thinky | 54.16% | $0.70 | — | $1 / $4.05 |
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


