Open FinLLM Reasoning — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 | 61.3 |
| 2 | GPT-4o | 61.01 |
| 3 | DeepSeek R1 | 60.87 |
| 4 | GPT-4.5 | 60.43 |
| 5 | Fino1-8B | 59.95 |
| 6 | DeepSeek R1 Distill Llama 70B | 59.27 |
| 7 | Fino1-14B | 58.1 |
| 8 | DeepSeek R1 Distill Qwen 32B | 57.4 |
| 9 | Qwen 2.5 32B Instruct | 56.17 |
| 10 | Llama 3.3 70B Instruct | 56.04 |
| 11 | O1 | 54.05 |
| 12 | Qwen 2.5 72B Instruct | 53.71 |
| 13 | DeepSeek R1 Distill Qwen 14B | 53.18 |
| 14 | QwQ-32B | 52.91 |
| 15 | Qwen 2.5 14B Instruct | 52.72 |
Interactive version: theaggregate.ai/benchmark?slug=open-finllm-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.