O1 Pro: benchmark results
OpenAI's pro-tier o1 variant using more inference compute. Provider: OpenAI. Released 2024-12-05. Access: API.
Aggregate Rating 1687 ± 26, rank #228 of 1656 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenAI ChatGPT Pro - AIME 2024 | 86 | pass@1 accuracy (%) | 100 |
| OpenAI ChatGPT Pro - AIME 2024 4/4 Reliability | 80 | 4/4 reliability (%) | 100 |
| OpenAI ChatGPT Pro - Codeforces | 90 | pass@1 percentile | 100 |
| OpenAI ChatGPT Pro - Codeforces 4/4 Reliability | 75 | 4/4 reliability percentile | 100 |
| OpenAI ChatGPT Pro - GPQA Diamond | 79 | pass@1 accuracy (%) | 100 |
| OpenAI ChatGPT Pro - GPQA Diamond 4/4 Reliability | 74 | 4/4 reliability (%) | 100 |
| SEAL - Agentic Tool Use (Enterprise) | 67.01 | Score | 93.9 |
| SEAL - Agentic Tool Use (Chat) | 61.42 | Score | 90.9 |
| NYT Connections Older Models | 74.6 | Score (%) | 90.2 |
| LLM Stats (AIME 2024) | 86 | Score (%) | 70.5 |
| SEAL - VISTA | 47.32 | Score | 69.8 |
| ZEROBench-Sub | 22.4 | Score (imported) | 60 |
Interactive version: theaggregate.ai/model?slug=o1-pro · How It Works · Data refreshed daily, snapshot 2026-10-20.