StakeBench — leaderboard
Metric: Agg (self-reported). Source: benchmarklist.com. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 20.4 |
| 2 | Qwen 3 32B | 17.6 |
| 3 | Gemini 2.5 Flash | 17.5 |
| 4 | Qwen 3 14B | 17.3 |
| 5 | Gemma 2 9B | 15.2 |
| 6 | Qwen 3 30B A3B | 14 |
| 7 | Claude Haiku 4.5 | 13.8 |
| 8 | Qwen 3 8B | 10.3 |
| 9 | Fino1-14B | 9.6 |
| 10 | Llama 3.2 3B | 9.2 |
| 11 | Fino1-8B | 7.2 |
| 12 | Mistral 7B | 4.5 |
Interactive version: theaggregate.ai/benchmark?slug=stakebench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.