reasoning benchmark
LiveCodeBench Leaderboard
LiveCodeBench is a benchmark for evaluating large language models on coding problems collected from LeetCode, AtCoder, and CodeForces.
Updated Sep 5, 2026
Models75
Model coverage75
MetricScore
EvidenceC
LiveCodeBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Score93.50% | Percentile100.00% | Participants75 | EvidenceC | Evaluated |
| Rank02 | ModelDE | Score91.60% | Percentile98.65% | Participants75 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score88.40% | Percentile97.30% | Participants75 | EvidenceC | Evaluated |
| Rank04 | ModelUP | Score87.80% | Percentile95.95% | Participants75 | EvidenceC | Evaluated |
| Rank05 | ModelDE | Score83.30% | Percentile94.59% | Participants75 | EvidenceC | Evaluated |
| Rank06 | ModelDE | Score83.30% | Percentile93.24% | Participants75 | EvidenceC | Evaluated |
| Rank07 | ModelMI | Score83.00% | Percentile91.89% | Participants75 | EvidenceC | Evaluated |
| Rank08 | ModelME | Score82.80% | Percentile90.54% | Participants75 | EvidenceC | Evaluated |
| Rank09 | ModelNV | Score81.19% | Percentile89.19% | Participants75 | EvidenceC | Evaluated |
| Rank10 | ModelXA | Score80.40% | Percentile87.84% | Participants75 | EvidenceC | Evaluated |
| Rank11 | ModelXA | Score80.00% | Percentile86.49% | Participants75 | EvidenceC | Evaluated |
| Rank12 | ModelXA | Score79.40% | Percentile85.14% | Participants75 | EvidenceC | Evaluated |
| Rank13 | ModelXA | Score79.40% | Percentile83.78% | Participants75 | EvidenceC | Evaluated |
| Rank14 | ModelME | Score79.40% | Percentile82.43% | Participants75 | EvidenceC | Evaluated |
| Rank15 | ModelXA | Score79.00% | Percentile81.08% | Participants75 | EvidenceC | Evaluated |
| Rank16 | ModelMI | Score78.00% | Percentile79.73% | Participants75 | EvidenceC | Evaluated |
| Rank17 | ModelAM Nova 2 ProAmazon | Score74.60% | Percentile78.38% | Participants75 | EvidenceC | Evaluated |
| Rank18 | ModelDE | Score74.10% | Percentile77.03% | Participants75 | EvidenceC | Evaluated |
| Rank19 | ModelDE | Score73.30% | Percentile75.68% | Participants75 | EvidenceC | Evaluated |
| Rank20 | ModelZA | Score72.90% | Percentile74.32% | Participants75 | EvidenceC | Evaluated |
| Rank21 | ModelNV | Score71.10% | Percentile72.97% | Participants75 | EvidenceC | Evaluated |
| Rank22 | ModelAMNova 2 LiteAmazon | Score71.00% | Percentile71.62% | Participants75 | EvidenceC | Evaluated |
| Rank23 | ModelZA | Score70.70% | Percentile70.27% | Participants75 | EvidenceC | Evaluated |
| Rank24 | ModelAC | Score70.70% | Percentile68.92% | Participants75 | EvidenceC | Evaluated |
| Rank25 | ModelGO | Score69.00% | Percentile67.57% | Participants75 | EvidenceC | Evaluated |
| Rank26 | ModelIN | Score67.00% | Percentile66.22% | Participants75 | EvidenceC | Evaluated |
| Rank27 | ModelNV | Score66.31% | Percentile64.86% | Participants75 | EvidenceC | Evaluated |
| Rank28 | ModelAC | Score65.70% | Percentile63.51% | Participants75 | EvidenceC | Evaluated |
| Rank29 | ModelMI | Score65.00% | Percentile62.16% | Participants75 | EvidenceC | Evaluated |
| Rank30 | ModelMA | Score64.60% | Percentile60.81% | Participants75 | EvidenceC | Evaluated |
LiveCodeBench Highlights
The leading models and scores on this benchmark.
LiveCodeBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LiveCodeBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is LiveCodeBench?
What LiveCodeBench measures and how its scores work.
LiveCodeBench continuously collects programming contest problems and annotates them with release dates to support evaluation on problems released after a model's training cutoff.
It measures Score, reported as a ratio, across code generation, self-repair, code execution, and test output prediction.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of C.
- Family
- LiveCodeBench
- 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.
Which model scores highest on LiveCodeBench?
DeepSeek-V4-Pro-Max is currently ranked first with 93.50%.
What are the top three models on LiveCodeBench?
The current leaders are DeepSeek-V4-Pro-Max (93.50%), DeepSeek-V4-Flash-Max (91.60%), and DeepSeek-V4-Flash-0423 (88.40%).
Which LiveCodeBench model has the lowest official input price?
Min istral 3 (3B Reasoning 2512) has the lowest matched official input price at $0.04 input / $0.04 output per 1M tokens.
Which models are fastest among LiveCodeBench results?
The fastest matched records are Min istral 3 (3B Reasoning 2512) (1,222.00 tok/s via Mistral AI), Llama 4 Scout (776.10 tok/s via Groq), and Mercury 2 (346.33 tok/s via Inception).
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.