LiveCodeBench v6
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.
Kimi K2.6 from Moonshot AI currently leads the LiveCodeBench v6 leaderboard with a score of 0.896 across 45 evaluated AI models.
Kimi K2.6 leads with 89.6%, followed by 
Seed 2.0 Pro at 87.8% and 
Qwen3.6 Plus at 87.1%.
Progress Over Time
Interactive timeline showing model performance evolution on LiveCodeBench v6
LiveCodeBench v6 Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Moonshot AI | 1.0T | 262K | $0.95 / $4.00 | ||
| 2 |  ByteDance | — | — | — | ||
| 3 |  Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 4 |  StepFun | 196B | 66K | $0.10 / $0.40 | ||
| 5 | Moonshot AI | 1.0T | — | — | ||
| 6 |  Zhipu AI | 358B | 205K | $0.60 / $2.20 | ||
| 7 | Alibaba Cloud / Qwen Team | 28B | 262K | $0.60 / $3.60 | ||
| 8 | Alibaba Cloud / Qwen Team | 397B | 262K | $0.60 / $3.60 | ||
| 9 | Moonshot AI | 1.0T | — | — | ||
| 10 | Zhipu AI | 357B | — | — | ||
| 11 |  OpenAI | 117B | 131K | $0.10 / $0.50 | ||
| 12 | ByteDance | — | — | — | ||
| 13 |  LG AI Research | 236B | — | — | ||
| 13 | Alibaba Cloud / Qwen Team | 27B | 262K | $0.30 / $2.40 | ||
| 15 |  Xiaomi | 309B | — | — | ||
| 16 | Alibaba Cloud / Qwen Team | 35B | — | — | ||
| 17 |  Google | 31B | 262K | $0.14 / $0.40 | ||
| 18 | Alibaba Cloud / Qwen Team | 122B | 262K | $0.40 / $3.20 | ||
| 19 | Google | 25B | 262K | $0.13 / $0.40 | ||
| 20 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.25 / $2.00 | ||
| 21 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 22 |  Sarvam AI | 105B | — | — | ||
| 23 | Alibaba Cloud / Qwen Team | 236B | 262K | $0.45 / $3.49 | ||
| 24 | Sarvam AI | 30B | — | — | ||
| 25 | Alibaba Cloud / Qwen Team | 1.0T | 256K | $0.50 / $5.00 | ||
| 26 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 27 | 32B | 262K | $0.06 / $0.24 | |||
| 28 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 28 | Alibaba Cloud / Qwen Team | 9B | — | — | ||
| 30 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 31 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.18 / $2.09 | ||
| 32 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 33 | Alibaba Cloud / Qwen Team | 4B | — | — | ||
| 34 | Alibaba Cloud / Qwen Team | 236B | 262K | $0.30 / $1.50 | ||
| 35 | Moonshot AI | 1.0T | — | — | ||
| 36 | Google | 8B | — | — | ||
| 36 |  OpenBMB | 9B | — | — | ||
| 38 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 39 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $1.00 | ||
| 40 | Google | 5B | — | — | ||
| 41 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 42 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 43 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.08 / $0.50 | ||
| 44 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $0.60 | ||
| 45 | Moonshot AI | 1.0T | — | — |
FAQ
Common questions about LiveCodeBench v6.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions