GPT-5 Nano (Medium): benchmark results
GPT-5 Nano evaluated at the medium reasoning-effort setting. Provider: OpenAI. Released 2025-08-07. Access: API.
Unified ELO 1528 ± 1, rank #725 of 1761 rated models, from 75 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MATH Level 5 | 95.24 | Accuracy (%) | 87 |
| AA LiveCodeBench | 76.3 | Pass@1 (%) | 83.1 |
| AA IFBench | 65.92 | Accuracy (%) | 77.4 |
| LisanBench | 0.08 | Mean Path Length / Current Maximum | 71.9 |
| AA AIME 2025 | 78.33 | Accuracy (%) | 71.1 |
| LLM Chess (Saplin) | 413.3 | ELO | 70.8 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 33.64 | Accuracy (%) | 69.1 |
| AI for Education Visual Maths - Algebra | 84.62 | Accuracy (%) | 64.9 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 20 | Accuracy (%) | 63 |
| SLR-Bench - Basic | 99 | Accuracy (%) | 62.7 |
| AI for Education Visual Maths - Measurement | 83.78 | Accuracy (%) | 60.8 |
| AI for Education Visual Maths - Statistics and Probability | 28.57 | Accuracy (%) | 60.8 |
Interactive version: theaggregate.ai/model?slug=gpt-5-nano-medium · How It Works · Data refreshed daily, snapshot 2026-09-05.