OpenAI ChatGPT Pro - Codeforces 4/4 Reliability: leaderboard
The "Codeforces 4/4 Reliability" subtask of OpenAI ChatGPT Pro. A benchmark result reported by OpenAI for ChatGPT Pro, as self-reported by the model developer.
Metric: 4/4 reliability percentile. Source: openai.com. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 Pro | 75 | #228 |
| 2 | O1 | 64 | #183 |
| 3 | O1 Preview | 26 | #193 |
Interactive version: theaggregate.ai/benchmark?slug=openai-chatgpt-pro-codeforces-4-4-reliability · How It Works · Data refreshed daily, snapshot 2026-10-20.