O4 Mini (Medium): benchmark results
O4 Mini evaluated at the medium reasoning-effort setting. Provider: OpenAI. Released 2025-04-16. Access: API.
Aggregate Rating 1662 ± 17, rank #486 of 2168 rated models, from 55 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TurtleAI | 15.92 | Success rate (%) on all 823 TurtleAI-DS tasks (102 real, 102 | 100 |
| TurtleAI - Hand-Drawn | 28.43 | Success rate (%) on the 102 TurtleAI-DSCraft tasks (hand-dra | 100 |
| TurtleAI - Synthetic | 10.5 | Success rate (%) on the 619 TurtleAI-DSSyn tasks (generated | 100 |
| MATH-Perturb (Hard) | 87.1 | Accuracy (%) | 94.4 |
| TurtleAI - Real | 36.27 | Success rate (%) on the 102 TurtleAI-DSReal tasks (XLogoOnli | 94.1 |
| LiveCodeBench | 84.5 | Pass@1 avg (%) | 92.6 |
| SEAL - VISTA | 51.66 | Score | 92.1 |
| UGI - Natural Intelligence | 43.66 | NatInt Score | 86.2 |
| IKP - T1 | 100 | Accuracy (%) | 86.1 |
| UGI - Writing | 45.39 | Writing Score | 83.9 |
| NYT Connections Older Models | 58.4 | Score (%) | 82.1 |
| IKP - T7 | 13.37 | Accuracy (%) | 80.9 |
Interactive version: theaggregate.ai/model?slug=o4-mini-medium · How It Works · Data refreshed daily, snapshot 2026-10-20.