Wikibench

SkillsBench

coding

Multilingual: no

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

Methodology

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

Leaderboard

Showing 3 of 3 results

  1. Qwen3.7 Max self-reported llm-stats
    59.2%
  2. Qwen3.6-27B self-reported llm-stats
    48.2%
  3. Qwen3.6 Plus self-reported llm-stats
    45.7%