GPT-5.4 Nano (Medium) — benchmark results
GPT-5.4 Nano evaluated at the medium reasoning-effort setting. Provider: OpenAI. Released 2026-03-17. Access: API.
Unified ELO 1583 ± 9, rank #520 of 1776 rated models, from 318 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish NLU - Sentiment Headlines ES | 53.49 | Sentiment classification Score (%) | 99.3 |
| EuroEval Portuguese NLU - ScaLA PT | 61.35 | Linguistic acceptability Score (%) | 96.6 |
| EuroEval Latvian NLU - Latvian Twitter Sentiment | 52.2 | Sentiment classification Score (%) | 96.1 |
| EuroEval Spanish NLU | 58.08 | NLU Average Score (%) | 95.4 |
| EuroEval Spanish NLU - ScaLA ES | 49.61 | Linguistic acceptability Score (%) | 95.4 |
| EuroEval Estonian NLU - Grammar ET | 48.69 | Linguistic acceptability Score (%) | 95.2 |
| EuroEval German NLU - ScaLA DE | 62.04 | Linguistic acceptability Score (%) | 95.1 |
| EuroEval Slovak NLU - ScaLA SK | 60.28 | Linguistic acceptability Score (%) | 94.6 |
| EuroEval Ukrainian Knowledge | 84.07 | Knowledge Average Score (%) | 94.6 |
| EuroEval Faroese NLU - FoSent | 70.97 | Sentiment classification Score (%) | 94.2 |
| EuroEval Polish Summarization - PSC | 25.21 | Score (%) | 93.9 |
| EuroEval Bosnian NLU - MMS BS | 50.56 | Sentiment classification Score (%) | 93.4 |
Interactive version: theaggregate.ai/model?slug=gpt-5-4-nano-medium · How the rankings work · Data refreshed daily, snapshot 2026-07-22.