# LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (LiveCodeBench)

> A continuously updated coding benchmark built from newly collected LeetCode, AtCoder, and Codeforces problems. Fresh problem windows reduce one contamination path, but results still need a release and setup check.

Canonical page: https://benchlm.ai/benchmarks/livecodebench

- Category: [Coding](/coding)
- Last updated: September 10, 2026

## About LiveCodeBench

- Year: 2024
- Tasks: Continuously updated contest problems
- Format: Competitive-programming evaluation
- Difficulty: Competitive programming level
- Paper: [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://arxiv.org/abs/2403.07974)

The official suite evaluates code generation, code execution, test-output prediction, and self-repair on contest problems added over time. Its releases and selectable date windows let evaluators separate older and newer problem sets instead of treating the benchmark as one fixed test.

LiveCodeBench is currently weighted in BenchLM's scoring formula. The Coding category carries 20% of the overall score, and LiveCodeBench contributes 15% of that category score.

## Leaderboard (7 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | 91.6% |
| 2 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | 89.6% |
| 3 | [Solar Pro 4](/models/solar-pro-4) | Upstage | 87.8% |
| 4 | [GLM-4.7](/models/glm-4-7) | Z.AI | 84.9% |
| 5 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | 83.9% |
| 6 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | 80.4% |
| 7 | [DeepSeek V3](/models/deepseek-v3) | DeepSeek | 37.6% |

## FAQ

### What does LiveCodeBench measure?

LiveCodeBench evaluates coding on newly collected contest problems from LeetCode, AtCoder, and Codeforces. Its suite covers code generation, execution, test-output prediction, and self-repair, although provider tables commonly report code-generation pass rates. It tests competitive-programming correctness, not work inside an existing software repository.

### Are LiveCodeBench scores directly comparable?

Only when the release, date window, scenario, pass@k metric, sampling count, temperature, and execution policy match. The official benchmark can change as new problems arrive, while providers may report different slices. BenchLM preserves sourced published rows, so unmatched settings support a directional read, not a precise ranking.

### Can LiveCodeBench pick the best coding agent?

No. A high score supports competitive-programming performance under the reported setup. It does not establish codebase navigation, issue interpretation, tool use, patch review, or regression safety. Pair LiveCodeBench with a repository benchmark such as SWE-bench Pro and a trial drawn from your own languages, libraries, and runtime constraints.

## Compare Top Models on LiveCodeBench

- [Qwen3.7 Max vs Qwen3.7 Plus](/compare/qwen3-7-max-vs-qwen3-7-plus)
- [Qwen3.7 Plus vs Solar Pro 4](/compare/qwen3-7-plus-vs-solar-pro-4)
- [Solar Pro 4 vs GLM-4.7](/compare/glm-4-7-vs-solar-pro-4)
- [GLM-4.7 vs Qwen3.6-27B](/compare/glm-4-7-vs-qwen3-6-27b)

## Related Reading

- [LiveCodeBench benchmark explainer](/blog/posts/livecodebench-contamination-free)