SciPaths — leaderboard
Metric: F1 (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 18.9 |
| 2 | GPT-5.4 | 15.2 |
| 3 | GPT-4.1 | 11.1 |
| 4 | GPT-5 Mini | 8.8 |
| 5 | Gemma 4 E4B | 6.1 |
| 6 | Qwen 3 4B Instruct | 6 |
| 7 | GPT-4o | 5.6 |
| 8 | Llama 3 8B Instruct | 4.1 |
| 9 | Llama 3.1 8B Instruct | 2.9 |
Interactive version: theaggregate.ai/benchmark?slug=scipaths · How the rankings work · Data refreshed daily, snapshot 2026-07-22.