GPT-5 Nano (Minimal) — benchmark results

GPT-5 Nano evaluated at the minimal reasoning-effort setting. Provider: OpenAI. Released 2025-08-07. Access: API.

Unified ELO 1422 ± 16, rank #1117 of 1776 rated models, from 152 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Icelandic Knowledge25.19Knowledge Average Score (%)71.8
EuroEval Portuguese Common Sense Reasoning64.14Common Sense Reasoning Average Score (%)70.6
AI for Education Visual Maths - Statistics and Probability28.57Accuracy (%)69.2
EuroEval Norwegian Common Sense Reasoning71.98Common Sense Reasoning Average Score (%)69.2
EuroEval Norwegian Knowledge32.46Knowledge Average Score (%)69.2
EuroEval English Knowledge82.05Knowledge Average Score (%)67.7
EuroEval Finnish Common Sense Reasoning44.76Common Sense Reasoning Average Score (%)67.1
EuroEval Portuguese NLU - MultiWikiQA PT71.71Reading comprehension Score (%)65.4
EuroEval Portuguese Knowledge54.49Knowledge Average Score (%)64.8
EuroEval Spanish NLU - ScaLA ES24.64Linguistic acceptability Score (%)64
EuroEval Dutch Knowledge58.31Knowledge Average Score (%)63.9
EuroEval Icelandic NLU - Hotter and Colder Sentiment39.06Sentiment classification Score (%)62.5

Interactive version: theaggregate.ai/model?slug=gpt-5-nano-minimal · How the rankings work · Data refreshed daily, snapshot 2026-07-22.