reasoning benchmark
LiveCodeBench(01-09)
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
LiveCodeBench(01-09) leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | DE | 41.8% | 100.0% | 1 | C |
LiveCodeBench(01-09) highlights
The top published results on this benchmark's own scale.
What is LiveCodeBench(01-09)?
Definition and scoring fields from the benchmark registry.
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- LiveCodeBench(01-09)
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- livecodebench(01-09)|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about LiveCodeBench(01-09).
Which model scores highest on LiveCodeBench(01-09)?
DeepSeek-V2.5 is currently ranked first with 41.8%.
What does LiveCodeBench(01-09) measure?
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.