ScienceArena (Text-Only Routes): leaderboard
ScienceArena (Zhao et al., 2026) evaluates language models on 13 recent science olympiad exams in physics, chemistry and biology, graded with the official process-credit rubrics by an LLM judge calibrated against medalist grading. The score is the mean of the 13 exam scores normalized to 0 to 100; this board holds text-only routes, which receive human-reviewed text renderings of the four 2026 contests, and higher is better.
Metric: Weighted average (0-100): mean of the 13 contest scores, each normalized to 0-100 by its full score, over IBO 2023, APhO, EuPhO, USNCO, IPhO, IChO, CPhO and CChO 2025 and INChO, NBPhO, USAPhO, IPhO and IChO 2026; 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; the nine other contests use text-only question renderings for every model and the four 2026 contests (NBPhO, USAPhO, IPhO and IChO 2026) are solved from Gemini 3.1 Pro-written, human-reviewed question-only text renderings (text-only routes). Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.7 Max | 79.3 | #145 |
| 2 | GLM-5.1 | 78.2 | #179 |
| 3 | DeepSeek V4 Pro | 77.1 | #188 |
| 4 | DeepSeek V4 Flash | 74.1 | #258 |
| 5 | MiMo-V2.5-Pro | 63.8 | #279 |
| 6 | MiniMax-M2.7 | 62.7 | #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-text-only-routes · How It Works · Data refreshed daily, snapshot 2026-11-13.