SuperCLUE-Law - Overall: leaderboard
SuperCLUE is the Chinese-language evaluation programme run by CLUE; its specialised boards each cover one professional domain and are graded by the organisers rather than self-reported. This board covers law: Chinese legal knowledge and reasoning.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around October 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 92.07 | #30 |
| 2 | Qwen 3.8 Max | 90.57 | #35 |
| 3 | Doubao-Seed-2.1-Pro (High) | 85.25 | |
| 4 | DeepSeek V4 Flash (Max) | 85.22 | #137 (DeepSeek V4 Flash) |
| 5 | Hy3 (High) | 83.42 | #93 (Hy3) |
| 6 | MiniMax-M3 | 80.04 | #136 |
| 7 | LongCat 2.0 | 77.51 | #219 |
| 8 | Step 3.7 Flash (High) | 77.19 | #236 (Step 3.7 Flash) |
| 9 | GLM-5.2 (Max) | 74.01 | #73 (GLM-5.2) |
| 10 | MiMo-V2.5-Pro | 68.5 | #158 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=superclue-law-overall · How It Works · Data refreshed daily, snapshot 2026-10-20.