FinEval 6.0: leaderboard
FinEval 6.0 evaluation report (Shanghai University of Finance and Economics, 2025): a Chinese financial-domain assessment across academic knowledge, safety awareness, industry understanding, agent application and financial rigor. Total score on a 0-100 scale; higher is better.
Metric: Total score (0-100). Source: github.com. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 32B (Thinking) | 84.53 | #960 (Qwen 3 32B) |
| 2 | Qwen 3 32B | 80.93 | #960 |
| 3 | GLM-Z1-32B-0414 | 80.13 | #755 |
| 4 | Qwen 3 30B A3B | 79.91 | #1124 |
| 5 | InternLM3-8B-Instruct | 78.48 | #2586 |
| 6 | GPT-4o | 77.65 | #741 |
| 7 | Llama 3.3 70B | 77.25 | #1511 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=fineval-6-0 · How It Works · Data refreshed daily, snapshot 2026-11-12.