SuperCLUE-Fin - 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 finance: Chinese financial knowledge, analysis and compliance.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around September 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 (Max) | 88.72 | #30 (Kimi K3) |
| 2 | Qwen 3.7 Max | 83.63 | #75 |
| 3 | Doubao-Seed-2.1-Pro (High) | 83.61 | |
| 4 | MiniMax-M3 | 82.13 | #136 |
| 5 | DeepSeek V4 Pro (Max) | 81.95 | #102 (DeepSeek V4 Pro) |
| 6 | Hy3 (High) | 81.28 | #93 (Hy3) |
| 7 | Kimi K2.6 | 74.65 | #104 |
| 8 | GLM-5.2 (Max) | 74.63 | #73 (GLM-5.2) |
| 9 | LongCat 2.0 | 73.45 | #219 |
| 10 | Step 3.7 Flash (High) | 72.61 | #236 (Step 3.7 Flash) |
| 11 | MiMo-V2.5-Pro | 72.14 | #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-fin-overall · How It Works · Data refreshed daily, snapshot 2026-10-20.