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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SciCode | 33.3 | Subproblem Resolve Rate (%) | 94.4 |
| ZebraLogic | 74.8 | Puzzle Accuracy (%) | 93.4 |
| AidanBench | 2300 | Novel Answers | 87.3 |
| FormationEval | 94.9 | Accuracy (%) | 69.7 |
| MATH-Perturb (Hard) | 78.49 | Accuracy (%) | 66.7 |
| SuperGPQA | 48.03 | Accuracy (%) | 60.3 |
| Wolfram LLM Benchmarking Project | 42.7 | Correct Functionality (%) | 53.8 |
| Epoch AI - ECI | 141.42 | ECI Score | 41.2 |
| LiveCodeBench | 70.6 | Pass@1 avg (%) | 37 |
| LLM Chess (Saplin) | -183.9 | ELO | 25.7 |
| SEAL - MASK | 49.73 | Score | 22 |
| LingOly-TOO | 12.2 | Obfuscated Score (self-reported) | 20 |
Interactive version: theaggregate.ai/model?slug=o3-mini-low · How the rankings work · Data refreshed daily, snapshot 2026-07-22.