math
GSM8K
Grade-school math word problems. 8500 human-generated arithmetic reasoning tasks. Now saturated at the frontier — replaced by MATH-500 and AIME for hard-math evaluation.
Official leaderboard →Top scores
| # | Model | Score |
|---|---|---|
| 1 | gpt-5 | 97.0% |
| 2 | claude-opus-4-8 | 96.4% |
| 3 | gemini-2-5-pro | 96.0% |
| 4 | llama-3-1-70b | 95.1% |
Scores are snapshots from public leaderboards at the time of last update. Follow the source link for the live board.