reasoning benchmark
OJBench Leaderboard
OJBench is a code reasoning benchmark containing 232 programming competition problems from NOI and ICPC across Easy, Medium, and Hard difficulty levels.
Updated Sep 5, 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 | Score60.60% | Percentile100.00% | Participants9 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score48.70% | Percentile87.50% | Participants9 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score40.10% | Percentile75.00% | Participants9 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score39.50% | Percentile62.50% | Participants9 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score36.00% | Percentile50.00% | Participants9 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score32.50% | Percentile37.50% | Participants9 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score29.70% | Percentile25.00% | Participants9 | EvidenceC | Evaluated |
| Rank08 | ModelMA | Score27.10% | Percentile12.50% | Participants9 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score27.10% | Percentile0.00% | 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.
What is OJBench?
What OJBench measures and how its scores work.
OJBench is a benchmark for assessing large language models on competitive programming problems using Python and C++.
It measures models' ability to solve complex competitive programming challenges, reported as a Score ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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 60.60%.
What are the top three models on OJBench?
The current leaders are Kimi K2.6 (60.60%), Kimi K2-Thinking-0905 (48.70%), and Qwen3.5-27B (40.10%).
Which OJBench model has the lowest official input price?
Qwen3.5-35B-A3B has the lowest matched official input price at $0.25 input / $2.0 output per 1M tokens.
Which models are fastest among OJBench results?
The fastest matched records are Kimi K2.6 (1.24 tok/s via Moonshot AI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.