GPT-5 Mini (Minimal) — benchmark results

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

Unified ELO 1518 ± 11, rank #735 of 1776 rated models, from 153 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Danish Knowledge92.56Knowledge Average Score (%)94.4
EuroEval Faroese NLU - FoQA76.55Reading comprehension Score (%)93.6
EuroEval Spanish NLU - MLQA ES67.81Reading comprehension Score (%)91.9
EuroEval Faroese NLU - FoSent64.41Sentiment classification Score (%)91.2
EuroEval Icelandic Knowledge42.84Knowledge Average Score (%)90.4
EuroEval French NLU - Allocine95.24Sentiment classification Score (%)88.8
AI for Education Visual Maths - Statistics and Probability42.86Accuracy (%)87.5
EuroEval Finnish Common Sense Reasoning65.33Common Sense Reasoning Average Score (%)87.2
EuroEval Portuguese Common Sense Reasoning85.47Common Sense Reasoning Average Score (%)87
EuroEval Faroese NLU - ScaLA FO20.14Linguistic acceptability Score (%)85.8
EuroEval Norwegian Knowledge43.99Knowledge Average Score (%)84.6
EuroEval Dutch NLU - SQuAD NL77.31Reading comprehension Score (%)83.2

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