STEMBench120 v1.0.0 (Closed Book) - Astronomy: leaderboard
Metric: Mean fractional scientific progress (0–4; 20 tasks/domain; zero-credit failures included). Source: www.ulam.ai. Saturation forecast: Around December 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4.1 Flash | 2.6 |
| 2 | Mistral Large 4 | 2.6 |
| 3 | Hy4 preview | 2.58 |
| 4 | MiMo-V2.6-Pro | 2.22 |
Interactive version: theaggregate.ai/benchmark?slug=stembench120-v1-0-0-closed-book-astronomy · How It Works · Data refreshed daily, snapshot 2026-10-10.