SuperCLUE-Fin (March 2026) - Overall: leaderboard
SuperCLUE-Fin evaluates Chinese financial LLM capability: financial knowledge, compliance and risk, financial calculation, investment research and advisory, and financial text understanding. March 2026 edition (2026年3月): headline 总分 of the 总榜单 sheet. Each dated workbook is a separate evaluation round, kept apart from the current board. Score 0-100, higher is better.
Metric: Score. Source: www.superclueai.com. Saturation forecast: Around February 2027. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao-Seed-2-0-Pro-260215 (High) | 79.8 | |
| 2 | GLM-5 | 78.67 | #149 |
| 3 | Kimi K2.5 (Thinking) | 77.89 | #152 (Kimi K2.5) |
| 4 | Qwen 3 Max | 76.95 | #213 |
| 5 | Qwen 3.5 397B A17B (Thinking) | 76.74 | #154 (Qwen 3.5 397B A17B) |
| 6 | MiniMax-M2.5 | 75.83 | #316 |
| 7 | Hunyuan-T1-20250822 | 75.63 | #306 |
| 8 | DeepSeek V3.2 (Thinking) | 75.47 | #210 (DeepSeek V3.2) |
| 9 | Gemini 2.5 Pro | 75.06 | #159 |
| 10 | Doubao-Seed-1.6-251015 (Thinking) | 74.42 | #208 (Doubao-Seed-1.6-251015) |
| 11 | GLM-4.6 | 72.77 | #265 |
| 12 | GPT-5 (High) | 72 | #105 (GPT-5) |
| 13 | MiniMax-M2 | 69.47 | #327 |
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-march-2026-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.