GPT-OSS-20B (Low) — benchmark results
GPT-OSS-20B evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2025-08-05. Access: Open.
Unified ELO 1543 ± 5, rank #643 of 1776 rated models, from 345 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Dutch Simplification - Duidelijke Taal | 56.94 | Score (%) | 97.7 |
| EuroEval Polish Summarization - PSC | 25.36 | Score (%) | 96.6 |
| EuroEval Spanish NLU - ScaLA ES | 44.57 | Linguistic acceptability Score (%) | 93.4 |
| EuroEval Portuguese NLU - ScaLA PT | 40.49 | Linguistic acceptability Score (%) | 90 |
| EuroEval Slovak NLU - UNER SK | 63.56 | Named entity recognition Score (%) | 89.7 |
| EuroEval Hungarian NLU - Szeged NER | 73.76 | Named entity recognition Score (%) | 89.6 |
| EuroEval Italian NLU - ScaLA IT | 41.68 | Linguistic acceptability Score (%) | 87.4 |
| EuroEval Croatian NLU - WikiANN HR | 66.58 | Named entity recognition Score (%) | 85.7 |
| EuroEval Portuguese NLU | 58.01 | NLU Average Score (%) | 85 |
| EuroEval Spanish NLU | 53.78 | NLU Average Score (%) | 84.9 |
| EuroEval English NLU - ScaLA EN | 55.84 | Linguistic acceptability Score (%) | 84.7 |
| EuroEval Czech NLU - PONER | 57.61 | Named entity recognition Score (%) | 84.6 |
Interactive version: theaggregate.ai/model?slug=gpt-oss-20b-low · How the rankings work · Data refreshed daily, snapshot 2026-07-22.