Open FinLLM Reasoning - DM-Simplong: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 60 |
| 2 | Qwen 2.5 72B Instruct | 59 |
| 3 | Qwen 2.5 14B Instruct | 59 |
| 4 | GPT-4.5 | 59 |
| 5 | Qwen 2.5 32B Instruct | 56 |
| 6 | O1 | 56 |
| 7 | DeepSeek R1 Distill Qwen 32B | 55 |
| 8 | Llama 3.3 70B Instruct | 54 |
| 9 | DeepSeek R1 | 53 |
| 10 | DeepSeek V3 | 53 |
| 11 | DeepSeek R1 Distill Llama 70B | 53 |
| 12 | Llama 3.1 70B Instruct | 48 |
| 13 | QwQ-32B | 46 |
| 14 | DeepSeek R1 Distill Qwen 14B | 44 |
| 15 | Qwen2.5-Math-72B-Instruct | 42 |
Interactive version: theaggregate.ai/benchmark?slug=open-finllm-reasoning-dm-simplong · How It Works · Data refreshed daily, snapshot 2026-09-05.