Back to explore

Benchmark Jev Skill Suggestion vs model Claude

Jev Skill Suggestion diuji terhadap model Claude dengan 26 skill, 10 prompt, dan 3 kali jalan: Jev akurasi 90% dan median 330ms; Haiku 80% dan 1,24 dtk; Sonnet/Opus/Fable 100% dan 2,2–4,5 dtk. Jev menukar sedikit akurasi dengan keputusan 4–14× lebih cepat.

I benchmarked Jev Skill Suggestion against Claude models with 26 skills, 10 prompts, and 3 runs each - Jev: 90% accuracy, 330ms median - Haiku: 80%, 1.24s - Sonnet/Opus/Fable: 100%, 2.2–4.5s So Jev trades a bit of accuracy for a 4–14× faster decision, while keeping the skill

Benchmark Jev Skill Suggestion vs model Claude 1
· 67 likesOpen on X