SciExam-ENSO - Physics: leaderboard

Metric: Physics score (0–1), final submitted model, six-hour budget. Source: github.com. Saturation forecast: Around March 2027. 13 models tracked.

Top models

#ModelScore
1Claude Fable 5.10.64
2GPT-6 Astra0.63
3GPT-5.50.6
4Claude Opus 50.59
5Kimi K30.57
6DeepSeek V4 Pro0.53
7GPT-5.6 Sol0.52
8DeepSeek V4.1 Flash0.51
9Gemini 3.8 Flash0.5
10MiniMax-M30.33
11GLM-5.20.26
12Qwen 3 Max0.06

Interactive version: theaggregate.ai/benchmark?slug=sciexam-enso-physics · How It Works · Data refreshed daily, snapshot 2026-10-09.