O1 (Medium): benchmark results
O1 evaluated at the medium reasoning-effort setting. Provider: OpenAI. Released 2024-12-05. Access: API.
Aggregate Rating 1636 ± 29, rank #577 of 2168 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Pedagogy - Social studies | 90 | Accuracy (%) | 97.3 |
| Gapminder AI Worldview | 90.9 | Correct Rate (%) | 94.1 |
| IKP - T2 | 100 | Accuracy (%) | 92.6 |
| IKP - T4 | 93.62 | Accuracy (%) | 90.3 |
| IKP - T7 | 15.12 | Accuracy (%) | 85.3 |
| IKP - T3 | 98.36 | Accuracy (%) | 84.4 |
| MATH Level 5 | 94.41 | Accuracy (%) | 84.1 |
| Incompressible Knowledge Probes (IKP) | 73.65 | Mean tier accuracy (%) | 82.6 |
| AI for Education Pedagogy - Science | 90.71 | Accuracy (%) | 81.4 |
| IKP - T5 | 77.35 | Accuracy (%) | 79.9 |
| AI for Education Pedagogy - Secondary | 86.64 | Accuracy (%) | 79.3 |
| IKP - T6 | 32.09 | Accuracy (%) | 78.6 |
Interactive version: theaggregate.ai/model?slug=o1-medium · How It Works · Data refreshed daily, snapshot 2026-10-20.