ScienceArena - USNCO 2025: leaderboard
Metric: Score (out of 100): points awarded on the US National Chemistry Olympiad 2025, 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: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 97 |
| 2 | Gemini 3.5 Flash | 95.7 |
| 3 | DeepSeek V4 Flash | 94.5 |
| 4 | Gemini 3 Flash | 93.5 |
| 5 | Qwen 3.7 Max | 93 |
| 6 | DeepSeek V4 Pro | 90 |
| 7 | GLM-5.1 | 90 |
| 8 | Qwen 3.6 Plus | 88.2 |
| 9 | GPT-5.4 | 76.9 |
| 10 | GPT-5.5 | 75.4 |
| 11 | Claude Opus 4.7 | 75.2 |
| 12 | MiMo-V2.5-Pro | 74 |
| 13 | Seed 2.0 Pro | 72.3 |
| 14 | MiniMax-M2.7 | 71.8 |
Interactive version: theaggregate.ai/benchmark?slug=sciencearena-usnco-2025 · How It Works · Data refreshed daily, snapshot 2026-09-29.