Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Skill-augmented Task Completion on SkillsBench 77 tasks (test)
Loading...
0.46
Mean Reward
Human
0.24056
0.29753
0.3545
0.41147
Jun 9, 2026
Mean Reward
95% CI
Gap Closed
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Reward
95% CI
Gap Closed
Human
Evaluation Protocol=Me...
2026.06
0.46
0.098
100
SKILLAXE
Evaluation Protocol=Me...
2026.06
0.273
0.084
11.4
LLM-self
Evaluation Protocol=Me...
2026.06
0.258
0.088
-
No-skill
Evaluation Protocol=Me...
2026.06
0.249
0.085
-
Feedback
Search any
task
Search any
task