ScienceArena - IChO 2025: leaderboard
Metric: Score (out of 60): points awarded on the International Chemistry Olympiad 2025 theory problems, text-only question renderings; interleaved solving, one subpart at a time with earlier turns in context; open-ended physics and chemistry turns graded against the official solution and process-credit rubric by the authors' medalist-calibrated LLM-judge pipeline. Source: arxiv.org. Saturation forecast: Around December 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 48.95 |
| 2 | Gemini 3.5 Flash | 47.98 |
| 3 | Gemini 3 Flash | 44.74 |
| 4 | Claude Opus 4.7 | 44.49 |
| 5 | Qwen 3.7 Max | 41.28 |
| 6 | GLM-5.1 | 38.82 |
| 7 | DeepSeek V4 Flash | 38.33 |
| 8 | Seed 2.0 Pro | 37.14 |
| 9 | Qwen 3.6 Plus | 36.22 |
| 10 | DeepSeek V4 Pro | 35.82 |
| 11 | GPT-5.5 | 35.77 |
| 12 | GPT-5.4 | 31.7 |
| 13 | MiMo-V2.5-Pro | 28.94 |
| 14 | MiniMax-M2.7 | 26.06 |
Interactive version: theaggregate.ai/benchmark?slug=sciencearena-icho-2025 · How It Works · Data refreshed daily, snapshot 2026-09-29.