GPT-5 Nano (2025-08-07) (Minimal): benchmark results
Provider: OpenAI. Released 2025-08-07. Access: API.
Unified ELO 1379 ± 22, rank #1538 of 2131 rated models, from 119 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Norwegian Knowledge - NRK Quiz QA | 46.56 | MCC (x100) | 76.4 |
| EuroEval Icelandic Knowledge | 25.19 | Knowledge Average Score (%) | 71.8 |
| EuroEval Portuguese Common Sense Reasoning | 64.14 | Common Sense Reasoning Average Score (%) | 70.6 |
| EuroEval Norwegian Common Sense Reasoning | 71.98 | Common Sense Reasoning Average Score (%) | 69.2 |
| EuroEval Norwegian Knowledge | 32.46 | Knowledge Average Score (%) | 69.2 |
| EuroEval Norwegian Knowledge - Idioms NO | 18.36 | MCC (x100) | 68.7 |
| EuroEval English Knowledge | 82.05 | Knowledge Average Score (%) | 67.7 |
| EuroEval Finnish Common Sense Reasoning | 44.76 | Common Sense Reasoning Average Score (%) | 67.1 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 71.71 | Reading comprehension Score (%) | 65.4 |
| EuroEval Portuguese Knowledge | 54.49 | Knowledge Average Score (%) | 64.8 |
| EuroEval Spanish NLU - ScaLA ES | 24.64 | Linguistic acceptability Score (%) | 64 |
| EuroEval Dutch Knowledge | 58.31 | Knowledge Average Score (%) | 63.9 |
Interactive version: theaggregate.ai/model?slug=gpt-5-nano-2025-08-07-minimal · How It Works · Data refreshed daily, snapshot 2026-10-09.