Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task with Predictable Failures on REALM-Bench P8
Loading...
3
Success Count
LG
2.85
2.925
3
3.075
May 5, 2026
Success Count
Tokens Consumed (k)
Latency (s)
Complexity Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
Success Count
Tokens Consumed (k)
Latency (s)
Complexity Score
LG
Framework=LG
2026.05
3
6
17
-
LG(PE)
Framework=LG(PE)
2026.05
3
13
18
-
SagaLLM
Framework=SagaLLM
2026.05
3
56
463
16
RAC
Framework=RAC
2026.05
3
33
32
3
RAC_M
Framework=RAC_M
2026.05
3
31
34
6.33
Feedback
Search any
task
Search any
task
