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++.
Kimi K2.6 from Moonshot AI currently leads the OJBench leaderboard with a score of 0.606 across 9 evaluated AI models.
What OJBench measures
OJBench is a text benchmark that evaluates large language models on reasoning tasks. LLM Stats tracks 9 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.4, with the leader reaching 0.6.
Compare leaders on the best AI for reasoning leaderboards.
Publication
- Paper
- 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.
Kimi K2.6 leads with 60.6%, followed by Kimi K2-Thinking-0905 at 48.7% and 
Qwen3.5-27B at 40.1%.
Progress Over Time
Interactive timeline showing model performance evolution on OJBench
OJBench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Moonshot AI | 1.0T | 262K | $0.95 / $4.00 | ||
| 2 | Moonshot AI | 1.0T | — | — | ||
| 3 |  Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 4 | Alibaba Cloud / Qwen Team | 122B | 262K | $0.40 / $3.20 | ||
| 5 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.25 / $2.00 | ||
| 6 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 8 | Moonshot AI | 1.0T | — | — | ||
| 8 | Moonshot AI | 1.0T | — | — |
FAQ
Common questions about OJBench.
Sub-benchmarks
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions