OJBench
Progress Over Time
Interactive timeline showing model performance evolution on OJBench
OJBench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Moonshot AI | 1.0T | 262K | $0.75 / $3.50 | ||
| 2 | Moonshot AI | 1.0T | — | — | ||
| 3 |  Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 4 | Alibaba Cloud / Qwen Team | 122B | — | — | ||
| 5 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 6 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 8 | Moonshot AI | 1.0T | — | — | ||
| 8 | Moonshot AI | 1.0T | — | — |
Sub-benchmarks
What is OJBench?
OJBench is a competition-level code benchmark designed to assess the competitive-level code reasoning abilities of large language models. It comprises 232 programming competition problems from NOI and ICPC, categorized into Easy, Medium, and Hard difficulty levels. The benchmark evaluates models' ability to solve complex competitive programming challenges using Python and C++.
OJBench is a text benchmark evaluating models on reasoning tasks. LLM Stats tracks 9 models on this benchmark, scored on a 0–1 scale. The current average is 0.4, with the leader at 0.6.
Compare leaders on the best AI for reasoning leaderboards.
Current leaders
Kimi K2.6 from Moonshot AI currently leads the OJBench leaderboard with a score of 0.606 across 9 evaluated AI models.
Source paper
- Title
- OJBench: A Competition Level Code Benchmark For Large Language Models
- Authors
- Zhexu Wang, Yiping Liu, Yejie Wang, Wenyang He, and 8 others
- Published
- arXiv
- 2506.16395
Abstract
Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spectrum of these capabilities, particularly at the competitive level. To bridge this gap, we introduce OJBench, a novel and challenging benchmark designed to assess the competitive-level code reasoning abilities of LLMs. OJBench comprises 232 programming competition problems from NOI and ICPC, providing a more rigorous test of models' reasoning skills. We conducted a comprehensive evaluation using OJBench on 37 models, including both closed-source and open-source models, reasoning-oriented and non-reasoning-oriented models. Our results indicate that even state-of-the-art reasoning-oriented models, such as o4-mini and Gemini-2.5-pro-exp, struggle with highly challenging competition-level problems. This highlights the significant challenges that models face in competitive-level code reasoning.
FAQ
Common questions about the OJBench benchmark and leaderboard.