Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Skill-assisted task execution on SkillsBench 1.0 (test)
Loading...
19.5
Pass@1
Oracle
8.788
11.569
14.35
17.131
Apr 8, 2025
Pass@1
Pass@3
Pass@3 (k=3)
Avg Steps per Task
Task Cost (USD)
Updated 2mo ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@3
Pass@3 (k=3)
Avg Steps per Task
Task Cost (USD)
Oracle
Skillset=Oracle
2025.04
19.5
35.4
6.2
20.1
0.028
SkillFlow
Skillset=SkillFlow
2025.04
16.4
29.2
4.6
18.8
0.025
Vercel
Skillset=Vercel
2025.04
9.7
20
1.5
20.9
0.029
No Skills
Skillset=No Skills
2025.04
9.2
16.9
0
18.7
0.026
Feedback
Search any
task
Search any
task
