HLCE — leaderboard
Humanity's Last Code Exam — 235 of the most challenging competitive programming problems from ICPC World Finals and IOI (2010-2024). Measures Pass@1 averaged across both contest types.
Metric: Pass@1 (%). Source: github.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O4 Mini (High) | 15.84 |
| 2 | Gemini 2.5 Pro (03-25) | 11.4 |
| 3 | O3 Mini (High) | 10.35 |
| 4 | O1 Mini | 5.95 |
| 5 | DeepSeek R1 | 4.83 |
| 6 | DeepSeek V3 (0324) | 3.53 |
| 7 | Claude 3.7 Sonnet | 2.48 |
| 8 | Claude 3.7 Sonnet (Thinking) | 2.12 |
| 9 | Claude 3.5 Sonnet | 1.71 |
| 10 | GPT-4o (2024-05-13) | 1.22 |
| 11 | GPT-4o ChatGPT | 1.18 |
| 12 | GPT-4o Mini | 0.48 |
Interactive version: theaggregate.ai/benchmark?slug=hlce · How the rankings work · Data refreshed daily, snapshot 2026-07-22.