StatABench — leaderboard
Metric: Total (self-reported). Source: benchmarklist.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 68.6 |
| 2 | Qwen 2.5 72B Instruct | 60.6 |
| 3 | DeepSeek V3 | 57.4 |
| 4 | Qwen 2.5 32B | 51.7 |
| 5 | GPT-4o Mini | 43.3 |
| 6 | Qwen 3 8B | 39.6 |
| 7 | Qwen 2.5 7B | 38.1 |
| 8 | Llama 3.1 8B | 25.5 |
Interactive version: theaggregate.ai/benchmark?slug=statabench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.