Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Skill Execution on SkillsBench Kimi CLI
Loading...
36
Success Count
SkCC
25.6
28.3
31
33.7
May 5, 2026
Success Count
Pass Rate
Mean Reward
Pass Rate (Baseline)
Pass Rate (Optimized)
Delta Pass Rate (pp)
Updated 28d ago
Evaluation Results
Method
Method
Links
Success Count
Pass Rate
Mean Reward
Pass Rate (Baseline)
Pass Rate (Optimized)
Delta Pass Rate (pp)
SkCC
Condition=Compiled, Ta...
2026.05
36
48.7
0.483
-
-
-
Kimi (Original)
Condition=Original, Ta...
2026.05
26
35.1
0.341
-
-
-
SkCC
Model=Kimi
2026.05
-
-
-
35.1
48.7
13.5
Liu et al.
Model=Kimi
2026.05
-
-
-
19.8
23.1
3.3
Feedback
Search any
task
Search any
task