Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Step-level failure attribution on Who&When (Alg)
Loading...
15,673.79
Input Tokens
Step-by-Step
2,793.9724
6,137.7712
9,481.57
12,825.3688
Jun 2, 2026
Input Tokens
Output Tokens
Latency (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Input Tokens
Output Tokens
Latency (s)
Step-by-Step
2026.06
15,673.79
1,626.2
26.18
Binary Search
2026.06
6,703.04
19.02
5.41
All-at-Once
2026.06
3,334.85
138.23
2.92
StepFinder
2026.06
3,289.35
0
0.61
Feedback
Search any
task
Search any
task