O4 Mini (Low) — benchmark results

O4 Mini evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2025-04-16. Access: API.

Unified ELO 1663 ± 29, rank #337 of 1776 rated models, from 30 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HAL SciCode9.23Accuracy (%)96.7
UGI - Natural Intelligence45.54NatInt Score89.1
UGI - Writing46.88Writing Score87.4
HAL AssistantBench28.05Accuracy (%)85.7
HAL USACO53.09Accuracy (%)81.8
HAL GAIA Level 353.85Accuracy (%)78.1
HAL SWE-bench Verified Mini54Score (%)76.5
HAL GAIA Level 171.7Accuracy (%)71.9
LLM Chess (Saplin)104.1ELO62.1
FormationEval94.3Accuracy (%)62
Epoch AI - ECI146.53ECI Score60.1
HAL ScienceAgentBench27.45Accuracy (%)60

Interactive version: theaggregate.ai/model?slug=o4-mini-low · How the rankings work · Data refreshed daily, snapshot 2026-07-22.