Codex Mini (Latest): benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1605 ± 42, rank #967 of 10916 rated models, from 3 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| WebApp1K Duo | 57.5 | Pass@1 (%) | 20.8 |
| ARC-AGI-1 | 27.33 | Accuracy (%) | 19.7 |
| ARC-AGI-2 | 1.27 | Accuracy (%) | 15.1 |
Interactive version: theaggregate.ai/model?slug=codex-mini-latest · How It Works · Data refreshed daily, snapshot 2026-11-08.