general
MMLU-Pro
Successor to MMLU with harder questions and 10 answer choices per question (vs. 4). Actively used for frontier-model differentiation.
Official leaderboard →Top scores
| # | Model | Score |
|---|---|---|
| 1 | gpt-5 | 84.0% |
| 2 | claude-opus-4-8 | 82.7% |
| 3 | gemini-2-5-pro | 82.1% |
| 4 | deepseek-v3 | 75.9% |
Scores are snapshots from public leaderboards at the time of last update. Follow the source link for the live board.