Open FinLLM Leaderboard: leaderboard
Open financial-language-model leaderboard from FINOS, covering broad financial NLP and reasoning task categories.
Metric: Average normalized score (imported). Source: finllm-leaderboard.readthedocs.io. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 48.34 | #438 |
| 2 | Qwen 2.5 32B Instruct | 42.49 | #498 |
| 3 | Qwen 2.5 72B Instruct | 41.36 | #454 |
| 4 | GPT-4o | 37.51 | #343 |
| 5 | Llama 3 70B Instruct | 31.23 | #634 |
| 6 | DeepSeek V3 Chat | 29.49 | #447 |
| 7 | GPT-4o Mini | 28.32 | #599 |
| 8 | GPT-3.5 Turbo (0125) | 23.16 | #984 |
| 9 | Llama 3.1 8B Instruct | 22.72 | #1035 |
| 10 | Gemma 2 27B (IT) | 19.81 | #645 |
| 11 | Llama 3 8B Instruct | 18.93 | #1129 |
| 12 | Qwen 2.5 7B Instruct | 17.37 | #862 |
| 13 | Mistral 7B Instruct (v0.3) | 14.68 | #1274 |
| 14 | Gemma 2 9B (IT) | 14.32 | #788 |
| 15 | Gemma 2 2B (IT) | 9.51 | #1341 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-finllm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.