SciPredict — leaderboard
SciPredict benchmarks LLMs on forecasting the outcomes of real scientific experiments across biology, chemistry, and physics.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 23.05 |
| 2 | Claude Sonnet 4.5 | 22.55 |
| 3 | Gemini 3 Flash (Preview) | 22.22 |
| 4 | Claude Opus 4.1 | 22.22 |
| 5 | GPT-5.2 | 20.58 |
| 6 | O3 Mini | 19.84 |
| 7 | Llama 3.3 70B Instruct | 18.19 |
| 8 | Gemini 2.5 Pro | 17.04 |
| 9 | Qwen 3 235B A22B | 16.63 |
| 10 | Llama 3.1 8B | 14.65 |
Interactive version: theaggregate.ai/benchmark?slug=scipredict · How the rankings work · Data refreshed daily, snapshot 2026-07-22.