Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Step-level failure attribution on Who&When HC
Loading...
79,817.71
Input Tokens
Step-by-Step
14,513.9156
31,467.7853
48,421.655
65,375.5247
Jun 2, 2026
Input Tokens
Output Tokens
Time (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Input Tokens
Output Tokens
Time (s)
Step-by-Step
2026.06
79,817.71
1,515.95
35.49
Binary Search
2026.06
34,771.07
16.57
6.92
StepFinder
2026.06
19,257.17
0
3.56
All-at-Once
2026.06
17,025.6
130.47
3.92
Feedback
Search any
task
Search any
task