reasoning benchmark
OJBench Leaderboard
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 17, 2026
Models9
Model coverage9
MetricScore
EvidenceB
OJBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score60.6% | Percentile100.0% | Participants9 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score48.7% | Percentile87.5% | Participants9 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score40.1% | Percentile75.0% | Participants9 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score39.5% | Percentile62.5% | Participants9 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score36.0% | Percentile50.0% | Participants9 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score32.5% | Percentile37.5% | Participants9 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score29.7% | Percentile25.0% | Participants9 | EvidenceC | Evaluated |
| Rank08 | ModelMA | Score27.1% | Percentile12.5% | Participants9 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score27.1% | Percentile0.0% | Participants9 | EvidenceC | Evaluated |
OJBench Highlights
The leading models and scores on this benchmark.
OJBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OJBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis ojbench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MAKimi K2.6Moonshot AI
- Score
- 60.6%
- Price
- $0.95 input / $4.0 output per 1M tokens
- Speed
- Up to 285 tok/s via Fireworks
Strengths
- Ranks #1 of 9 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures OJBench, not total model capability
- 02MAKimi K2-Thinking-0905Moonshot AI
- Score
- 48.7%
- Price
- $0.60 input / $2.5 output per 1M tokens
Strengths
- Ranks #2 of 9 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures OJBench, not total model capability
- 03ACQwen3.5-27BAlibaba Cloud / Qwen Team
- Score
- 40.1%
- Price
- $0.30 input / $2.4 output per 1M tokens
- Speed
- Up to 6.7 tok/s via Novita
Strengths
- Ranks #3 of 9 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures OJBench, not total model capability
- 04ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Score
- 39.5%
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #4 of 9 compared models
- 63th percentile on this benchmark
- C evidence result
Considerations
- This result measures OJBench, not total model capability
- 05ACQwen3.5-35B-A3BAlibaba Cloud / Qwen Team
- Score
- 36.0%
- Price
- $0.25 input / $2.0 output per 1M tokens
Strengths
- Ranks #5 of 9 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures OJBench, not total model capability
Selection summary
Best AI Models for OJBench
Kimi K2.6 currently leads OJBench with 60.6%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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.