reasoning benchmark
LiveCodeBench v5
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 models9
Registry coverage9
MetricScore
EvidenceB
LiveCodeBench v5 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | GO | 75.6% | 100.0% | 9 | C | |
| 2 | GO | 63.9% | 87.5% | 9 | C | |
| 3 | AC | 61.4% | 75.0% | 9 | C | |
| 4 | OP | 60.5% | 62.5% | 9 | C | |
| 5 | GO | 28.9% | 50.0% | 9 | C | |
| 6 | GO | 25.7% | 37.5% | 9 | C | |
| 7 | GO | 25.7% | 25.0% | 9 | C | |
| 8 | GO | 18.6% | 12.5% | 9 | C | |
| 9 | GO | 18.6% | 0.0% | 9 | C |
Score distribution
Top published rows on the benchmark's original scale.
LiveCodeBench v5 highlights
The top published results on this benchmark's own scale.
What is LiveCodeBench v5?
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 v5
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- livecodebench-v5|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about LiveCodeBench v5.
Which model scores highest on LiveCodeBench v5?
Gemini 2.5 Pro is currently ranked first with 75.6%.
What does LiveCodeBench v5 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?
9 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.