GPT-5 Mini (2025-08-07) (High): benchmark results
Provider: OpenAI. Released 2025-08-07. Access: API.
Unified ELO 1649 ± 15, rank #515 of 2131 rated models, from 143 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval German NLU - Sb10K | 64.63 | Sentiment classification Score (%) | 99.7 |
| EuroEval Portuguese Knowledge | 90.72 | Knowledge Average Score (%) | 98.9 |
| EuroEval French Knowledge | 85.28 | Knowledge Average Score (%) | 98.5 |
| EuroEval Italian Knowledge | 87.24 | Knowledge Average Score (%) | 98.2 |
| MATH Level 5 | 97.85 | Accuracy (%) | 98.1 |
| EuroEval Icelandic Common Sense Reasoning | 85.66 | Common Sense Reasoning Average Score (%) | 97.5 |
| EuroEval German Knowledge | 86.71 | Knowledge Average Score (%) | 97.4 |
| EuroEval English Knowledge | 95.02 | Knowledge Average Score (%) | 97.3 |
| EuroEval Norwegian Knowledge - Idioms NO | 69.06 | MCC (x100) | 97.2 |
| EuroEval Norwegian | 70.3 | Average Score (%) | 97.1 |
| EuroEval Norwegian Knowledge | 71.74 | Knowledge Average Score (%) | 97 |
| EuroEval Dutch NLU - DBRD | 93.15 | Sentiment classification Score (%) | 96.9 |
Interactive version: theaggregate.ai/model?slug=gpt-5-mini-2025-08-07-high · How It Works · Data refreshed daily, snapshot 2026-10-09.