Fin-RATE: leaderboard
Financial analytics benchmark over SEC filings covering detail/reasoning QA, enterprise comparison QA, and longitudinal tracking QA.
Metric: Macro Accuracy (self-reported). Source: benchmarklist.com. Status: saturation imminent. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 33.24 |
| 2 | Qwen 3 235B A22B | 24.39 |
| 3 | GPT-OSS-20B | 18.69 |
| 4 | MiMo-V2-Flash | 18.05 |
| 5 | Qwen 3 30B A3B 2507 Instruct | 17.63 |
| 6 | Llama 3.3 70B Instruct | 16.76 |
| 7 | DeepSeek V3.2 | 16.32 |
| 8 | DeepSeek R1 | 15.53 |
| 9 | Qwen 3 14B | 11.25 |
| 10 | DeepSeek V3 | 9.81 |
| 11 | Qwen 3 8B | 5.48 |
Interactive version: theaggregate.ai/benchmark?slug=fin-rate · How It Works · Data refreshed daily, snapshot 2026-09-05.