Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Retrieval-Augmented Generation on ASQA
Loading...
42.44
str-EM
ConsJudge
33.08
35.51
37.94
40.37
Feb 26, 2025
str-EM
Updated 4d ago
Evaluation Results
Method
Method
Links
str-EM
ConsJudge
Generator=Llama3-8B-In...
2025.02
42.44
Raw Metric
Generator=Llama3-8B-In...
2025.02
41.55
Vanilla LLM
Generator=Llama3-8B-In...
2025.02
40.69
SFT
Generator=Llama3-8B-In...
2025.02
40.37
ConsJudge
Generator=MiniCPM-2.4B...
2025.02
36.45
Vanilla LLM
Generator=MiniCPM-2.4B...
2025.02
35.77
ConsJudge
Generator=MiniCPM-2.4B...
2025.02
35.68
Vanilla LLM
Generator=MiniCPM-2.4B...
2025.02
34.95
SFT
Generator=MiniCPM-2.4B...
2025.02
34.6
SFT
Generator=MiniCPM-2.4B...
2025.02
33.51
Raw Metric
Generator=MiniCPM-2.4B...
2025.02
33.44
Feedback
Search any
task
Search any
task