SkillMutator
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
SkillMutator GPT-5.4 adversarial-oracle (evaluable)
86.8Detection Rate
9
SkillMutator GPT-5.4-mini adversarial-oracle evaluable subset (n=63)
88.9Detection Rate
9
SkillMutator GPT-4o-mini adversarial-oracle evaluable subset (n=48)
89.6Detection Rate
9