ScienceArena - CChO 2025: leaderboard

The Chinese Chemistry Olympiad 2025 final in ScienceArena (Zhao et al., 2026), solved one subpart at a time from text renderings of the questions. Points out of 100, awarded by an LLM judge applying the official process-credit rubric, calibrated against medalist grading; higher is better.

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 February 2027. 14 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)72.28#94
2Gemini 3.5 Flash70.6#101
3Gemini 3 Flash59.55#164
4GLM-5.158.61#179
5Claude Opus 4.756.59#79
6GPT-5.553.3#49
7Seed 2.0 Pro53.18#211
8Qwen 3.7 Max52.66#145
9MiMo-V2.5-Pro50.11#279
10DeepSeek V4 Pro49.78#188
11Qwen 3.6 Plus49.33#222
12GPT-5.447.79#123
13DeepSeek V4 Flash46.46#258
14MiniMax-M2.743.78#518

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=sciencearena-ccho-2025 · How It Works · Data refreshed daily, snapshot 2026-11-13.