SciEval - Astronomy — leaderboard
Metric: Astronomy (%). Source: huggingface.co. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 Max | 75.64 |
| 2 | Ling-flash-2.0 | 48.12 |
| 3 | GPT-5 | 44.57 |
| 4 | Gemini 2.5 Pro | 43.4 |
| 5 | O3 | 42.82 |
| 6 | Gemini 3 Pro | 42.23 |
| 7 | GPT-5.1 | 42.02 |
| 8 | Kimi K2 | 35.57 |
| 9 | Claude Sonnet 4.5 | 34.23 |
| 10 | Grok 2 (1212) | 33.51 |
| 11 | Gemini 2.5 Flash | 31.94 |
| 12 | Llama 4 Maverick | 31.91 |
| 13 | GPT-4o | 30.73 |
| 14 | Qwen 3 VL 235B A22B | 29.84 |
| 15 | Intern-S1 | 29.55 |
Interactive version: theaggregate.ai/benchmark?slug=scieval-astronomy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.