reasoning benchmark
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++.
Updated Aug 11, 2026
Models9
Model coverage9
MetricScore
EvidenceB
OJBench Ranking
Higher score ranks better on this benchmark.
| 1 | MA | 60.6% | 100.0% | 9 | C | |
| 2 | MA | 48.7% | 87.5% | 9 | C | |
| 3 | AC | 40.1% | 75.0% | 9 | C | |
| 4 | AC | 39.5% | 62.5% | 9 | C | |
| 5 | AC | 36.0% | 50.0% | 9 | C | |
| 6 | AC | 32.5% | 37.5% | 9 | C | |
| 7 | AC | 29.7% | 25.0% | 9 | C | |
| 8 | MA | 27.1% | 12.5% | 9 | C | |
| 9 | MA | 27.1% | 0.0% | 9 | C |
OJBench Score Distribution
A closer view of the leading scores on this benchmark.
OJBench Highlights
The leading models and scores on this benchmark.
What is OJBench?
What OJBench measures and how its scores work.
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++.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OJBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- ojbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OJBench.
Which model scores highest on OJBench?
Kimi K2.6 is currently ranked first with 60.6%.
What does OJBench measure?
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++.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
9 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.