Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Failure Attribution Accuracy on Who&When (Alg)
Loading...
42.86
Accuracy (Who&When Alg)
AgenTracer
10.6616
19.0208
27.38
35.7392
Jun 2, 2026
Accuracy (Who&When Alg)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Who&When Alg)
AgenTracer
evaluation with ground...
2026.06
42.86
AgenTracer
2026.06
37.3
CDC-MAS
2026.06
36.2
StepFinder
2026.06
29.63
StepFinder
Category=Sequential, E...
2026.06
29.63
Transformer
Category=Sequential, L...
2026.06
24.87
TCN
Category=Sequential, L...
2026.06
24.34
BiGRU
Category=Sequential, L...
2026.06
23.28
Step-by-Step (G)
Category=LLM-based, LL...
2026.06
20.11
Binary Search (G)
Category=LLM-based, LL...
2026.06
20.1
All-at-Once (G)
Category=LLM-based, LL...
2026.06
15.87
Binary Search
Category=LLM-based, LL...
2026.06
15.61
Random
Category=Baseline
2026.06
15.08
Step-by-Step
Category=LLM-based, LL...
2026.06
14.02
All-at-Once
Category=LLM-based, LL...
2026.06
11.9
Feedback
Search any
task
Search any
task