Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Retrieval-Augmented Generation on MARCOQA
Loading...
88.25
LLM Score
ConsJudge
84.61
85.555
86.5
87.445
Feb 26, 2025
LLM Score
Updated 4d ago
Evaluation Results
Method
Method
Links
LLM Score
ConsJudge
Generator=Llama3-8B-In...
2025.02
88.25
Vanilla LLM
Generator=Llama3-8B-In...
2025.02
88.15
SFT
Generator=Llama3-8B-In...
2025.02
87.46
SFT
Generator=MiniCPM-2.4B...
2025.02
86.35
ConsJudge
Generator=MiniCPM-2.4B...
2025.02
86.16
Vanilla LLM
Generator=MiniCPM-2.4B...
2025.02
86
SFT
Generator=MiniCPM-2.4B...
2025.02
85.9
ConsJudge
Generator=MiniCPM-2.4B...
2025.02
85.73
Vanilla LLM
Generator=MiniCPM-2.4B...
2025.02
85.59
Raw Metric
Generator=Llama3-8B-In...
2025.02
84.8
Raw Metric
Generator=MiniCPM-2.4B...
2025.02
84.75
Feedback
Search any
task
Search any
task