GPT-5.4 Mini (Low): benchmark results
Provider: OpenAI. Released 2026-03-17. Access: API.
Unified ELO 1629 ± 11, rank #585 of 2088 rated models, from 302 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Albanian NLU - MMS SQ | 30.83 | Sentiment classification Score (%) | 99.5 |
| EuroEval Croatian NLU | 60.64 | NLU Average Score (%) | 99.5 |
| EuroEval Swedish NLU - SUC3 | 81.61 | Named entity recognition Score (%) | 99.5 |
| EuroEval Slovene NLU - ScaLA SL | 64.04 | Linguistic acceptability Score (%) | 99 |
| EuroEval Lithuanian NLU | 56.71 | NLU Average Score (%) | 98.7 |
| EuroEval English NLU - ScaLA EN | 68.73 | Linguistic acceptability Score (%) | 98.5 |
| EuroEval Spanish NLU | 61.46 | NLU Average Score (%) | 98.5 |
| EuroEval Czech NLU | 60.89 | NLU Average Score (%) | 98.2 |
| EuroEval French NLU - Eltec | 76.02 | Named entity recognition Score (%) | 98.1 |
| EuroEval Portuguese NLU - ScaLA PT | 67.3 | Linguistic acceptability Score (%) | 98 |
| EuroEval Slovene NLU | 62.25 | NLU Average Score (%) | 98 |
| EuroEval Dutch NLU - DBRD | 93.45 | Sentiment classification Score (%) | 97.8 |
Interactive version: theaggregate.ai/model?slug=gpt-5-4-mini-low · How It Works · Data refreshed daily, snapshot 2026-10-07.