ScienceArena - CChO 2025: leaderboard

Metric: Score (out of 100): points awarded on the Chinese Chemistry Olympiad 2025 final, 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

#ModelScore
1Gemini 3.1 Pro (Preview)72.28
2Gemini 3.5 Flash70.6
3Gemini 3 Flash59.55
4GLM-5.158.61
5Claude Opus 4.756.59
6GPT-5.553.3
7Seed 2.0 Pro53.18
8Qwen 3.7 Max52.66
9MiMo-V2.5-Pro50.11
10DeepSeek V4 Pro49.78
11Qwen 3.6 Plus49.33
12GPT-5.447.79
13DeepSeek V4 Flash46.46
14MiniMax-M2.743.78

Interactive version: theaggregate.ai/benchmark?slug=sciencearena-ccho-2025 · How It Works · Data refreshed daily, snapshot 2026-09-29.