Fin-Bias — leaderboard
Metric: Average Herding Score (with rating) (self-reported). Source: benchmarklist.com. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 8B | 98.3 |
| 2 | GLM-4 9B Chat | 98.1 |
| 3 | gemma-7B (IT) | 97.6 |
| 4 | Gemma 2 27B | 97.5 |
| 5 | Claude 3.5 Haiku | 97.1 |
| 6 | Gemma 2 9B (IT) | 97 |
| 7 | GPT-4 | 95.9 |
| 8 | GPT-5 | 94.6 |
| 9 | Llama 3.1 8B IT | 92.4 |
| 10 | Mistral Nemo Instruct (2407) | 90.8 |
| 11 | Claude Sonnet 4 | 90.6 |
| 12 | internlm2-chat-7B | 89.1 |
| 13 | Yi-1.5-9B-Chat-16K | 83.4 |
Interactive version: theaggregate.ai/benchmark?slug=fin-bias · How the rankings work · Data refreshed daily, snapshot 2026-07-22.