Wikibench

LiveCodeBench v6

reasoning official site →

Multilingual: no

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.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: general, reasoning. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 20 of 42 results

  1. Qwen3.7 Max self-reported llm-stats
    91.6%
  2. Kimi K2.6 self-reported llm-stats
    89.6%
  3. Seed 2.0 Pro self-reported llm-stats
    87.8%
  4. MAI-Thinking-1 self-reported llm-stats
    87.7%
  5. Qwen3.6 Plus self-reported llm-stats
    87.1%
  6. Step-3.5-Flash self-reported llm-stats
    86.4%
  7. Kimi K2.5 self-reported llm-stats
    85.0%
  8. GLM-4.7 self-reported llm-stats
    84.9%
  9. Qwen3.6-27B self-reported llm-stats
    83.9%
  10. Qwen3.5-397B-A17B self-reported llm-stats
    83.6%
  11. Kimi K2-Thinking-0905 self-reported llm-stats
    83.1%
  12. GLM-4.6 self-reported llm-stats
    82.8%
  13. GPT OSS 120B High self-reported llm-stats
    81.9%
  14. K-EXAONE-236B-A23B self-reported llm-stats
    80.7%
  15. Qwen3.5-27B self-reported llm-stats
    80.7%
  16. MiMo-V2-Flash self-reported llm-stats
    80.6%
  17. Gemma 4 31B self-reported llm-stats
    80.0%
  18. Qwen3.5-122B-A10B self-reported llm-stats
    78.9%
  19. Gemma 4 26B-A4B self-reported llm-stats
    77.1%
  20. Qwen3.5-35B-A3B self-reported llm-stats
    74.6%