UOJ-Bench - Hacking (Hard): leaderboard
Metric: Pass@1 (%) on the 1,046 hard hacking instances (accepted submissions later broken by community hacks, covert errors): the generated input-synthesis script must make the target submission fail on UOJ, single-turn zero-shot Pass@1 judged by the Universal Online Judge through its internal API (problem statements translated from Chinese to English; maximum response length at least 64k tokens); higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 44.17 |
| 2 | GPT-5 | 38.15 |
| 3 | GPT-5 (High) | 36.9 |
| 4 | Kimi K2 (Thinking) | 28.2 |
| 5 | DeepSeek V3.2 (Thinking) | 25.43 |
| 6 | GPT-OSS-120B | 20.17 |
| 7 | Claude Opus 4.5 | 8.99 |
| 8 | Qwen 3 Coder 480B A35B Instruct | 5.64 |
Interactive version: theaggregate.ai/benchmark?slug=uoj-bench-hacking-hard · How It Works · Data refreshed daily, snapshot 2026-09-29.