reasoning benchmark
LiveCodeBench Pro
LiveCodeBench Pro is an advanced evaluation benchmark for large language models for code that uses Elo ratings to rank models based on their performance on coding tasks. It evaluates models on real-world coding problems from programming contests (LeetCode, AtCoder, CodeForces) and provides a relative ranking system where higher Elo scores indicate superior performance.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
LiveCodeBench Pro leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | GO | 2,887 points | 100.0% | 4 | C | |
| 2 | GO | 2,439 points | 66.7% | 4 | C | |
| 3 | ME | 0.8 points | 33.3% | 4 | C | |
| 4 | GO | 2,316 points | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
LiveCodeBench Pro highlights
The top published results on this benchmark's own scale.
What is LiveCodeBench Pro?
Definition and scoring fields from the benchmark registry.
LiveCodeBench Pro is an advanced evaluation benchmark for large language models for code that uses Elo ratings to rank models based on their performance on coding tasks. It evaluates models on real-world coding problems from programming contests (LeetCode, AtCoder, CodeForces) and provides a relative ranking system where higher Elo scores indicate superior performance.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- LiveCodeBench Pro
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- livecodebench-pro|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about LiveCodeBench Pro.
Which model scores highest on LiveCodeBench Pro?
Gemini 3.1 Pro is currently ranked first with 2,887 points.
What does LiveCodeBench Pro measure?
LiveCodeBench Pro is an advanced evaluation benchmark for large language models for code that uses Elo ratings to rank models based on their performance on coding tasks. It evaluates models on real-world coding problems from programming contests (LeetCode, AtCoder, CodeForces) and provides a relative ranking system where higher Elo scores indicate superior performance.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 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.