reasoning benchmark
LiveCodeBench v5 Leaderboard
LiveCodeBench v5 is a benchmark for evaluating large language models on code using newly collected programming contest problems.
Updated Sep 5, 2026
Models9
Model coverage9
MetricScore
EvidenceB
LiveCodeBench v5 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score75.60% | Percentile100.00% | Participants9 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score63.90% | Percentile87.50% | Participants9 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score61.40% | Percentile75.00% | Participants9 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score60.48% | Percentile62.50% | Participants9 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score28.90% | Percentile50.00% | Participants9 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score25.70% | Percentile37.50% | Participants9 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score25.70% | Percentile25.00% | Participants9 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score18.60% | Percentile12.50% | Participants9 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score18.60% | Percentile0.00% | Participants9 | EvidenceC | Evaluated |
LiveCodeBench v5 Highlights
The leading models and scores on this benchmark.
LiveCodeBench v5 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LiveCodeBench v5
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is LiveCodeBench v5?
What LiveCodeBench v5 measures and how its scores work.
LiveCodeBench v5 is a code evaluation benchmark that collects problems from LeetCode, AtCoder, and CodeForces and annotates them with release dates.
It measures code generation, self-repair, code execution, and test output prediction using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- LiveCodeBench v5
- 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 LiveCodeBench v5.
Which model scores highest on LiveCodeBench v5?
Gemini 2.5 Pro is currently ranked first with 75.60%.
What are the top three models on LiveCodeBench v5?
The current leaders are Gemini 2.5 Pro (75.60%), Gemini 2.5 Flash (63.90%), and Qwen3 VL 235B A22B Instruct (61.40%).
Which LiveCodeBench v5 model has the lowest official input price?
Gemini 2.5 Flash has the lowest matched official input price at $0.30 input / $2.5 output per 1M tokens.
Which models are fastest among LiveCodeBench v5 results?
The fastest matched records are Gemini 2.5 Flash (85.00 tok/s via Google), Gemini 2.0 Flash-Lite (85.00 tok/s via Google), and Gemini 2.5 Pro (18.89 tok/s via Google).
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.