all the models — AI benchmark observatory
← Benchmarks

SkillsBench

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

id skillsbench · max 1 · 11 models reported

#ModelScore
1Qwen3.8 Max
Alibaba Cloud / Qwen Team · open
0.70
SkillsBench Leaderboard · all the models