reasoning
GPQA Diamond
Graduate-level Google-proof Q&A — 198 physics/chem/bio questions written by domain PhDs and verified to be non-Google-answerable. Expert baseline is ~65%.
Official leaderboard →Top scores
| # | Model | Score |
|---|---|---|
| 1 | o3 | 87.7% |
| 2 | claude-opus-4-8 | 79.6% |
| 3 | gpt-5 | 78.4% |
| 4 | gemini-2-5-pro | 75.8% |
| 5 | deepseek-r1 | 71.5% |
Scores are snapshots from public leaderboards at the time of last update. Follow the source link for the live board.