O3 Mini (Low) — benchmark results

O3 Mini evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2025-01-31. Access: API.

Unified ELO 1569 ± 43, rank #569 of 1776 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SciCode33.3Subproblem Resolve Rate (%)94.4
ZebraLogic74.8Puzzle Accuracy (%)93.4
AidanBench2300Novel Answers87.3
FormationEval94.9Accuracy (%)69.7
MATH-Perturb (Hard)78.49Accuracy (%)66.7
SuperGPQA48.03Accuracy (%)60.3
Wolfram LLM Benchmarking Project42.7Correct Functionality (%)53.8
Epoch AI - ECI141.42ECI Score41.2
LiveCodeBench70.6Pass@1 avg (%)37
LLM Chess (Saplin)-183.9ELO25.7
SEAL - MASK49.73Score22
LingOly-TOO12.2Obfuscated Score (self-reported)20

Interactive version: theaggregate.ai/model?slug=o3-mini-low · How the rankings work · Data refreshed daily, snapshot 2026-07-22.