O1 Preview (2024-09-12): benchmark results
September 12, 2024 O1 Preview snapshot, tracked when sources report the dated API model. Provider: OpenAI. Released 2024-09-12. Access: API.
Unified ELO 1576 ± 1, rank #335 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ZebraLogic | 71.4 | Puzzle Accuracy (%) | 91.8 |
| Wolfram LLM Benchmarking Project | 52.2 | Correct Functionality (%) | 74.1 |
| TextClass Benchmark | 1622.24 | Meta-Elo (self-reported) | 72 |
| MATH Level 5 | 81.65 | Accuracy (%) | 65.7 |
| CRUST-bench | 15 | Pass@1 Test Success (%) | 64.3 |
| BIRD-CRITIC | 33.33 | Score | 60 |
| WritingBench | 63.44 | Score (self-reported) | 29.6 |
| OTIS Mock AIME 2024-25 | 31.11 | Accuracy (%) | 27.3 |
| SpeechMap Compliance | 35.8 | % Requests Completed | 13.2 |
Interactive version: theaggregate.ai/model?slug=o1-preview-2024-09-12 · How It Works · Data refreshed daily, snapshot 2026-09-05.