GPQA Diamond

Graduate-level, Google-proof questions in biology, physics, and chemistry that demand expert reasoning.

Reasoning

Expert research High-stakes analysis Scientific Q&A

Higher is better · accuracy %

1 Claude Opus 5 62.4%

2 Gemini 2.5 Pro 60.1%

3 DeepSeek-V4 Flash 55.8%

4 Claude Sonnet 5 54.2%

Bars scaled from 45 so close scores stay legible — the figure at right is the actual accuracy %.