Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Explanation Faithfulness Evaluation on Math Book (test)
Loading...
31.4
Greedy Score
DPO + RMD
23.288
25.394
27.5
29.606
Apr 7, 2025
Greedy Score
Majority Voting Score (@16)
Updated 18d ago
Evaluation Results
Method
Method
Links
Greedy Score
Majority Voting Score (@16)
DPO + RMD
Base Model=LLAMA-3.2-3...
2025.04
31.4
40.2
DPO + RM
Base Model=LLAMA-3.2-3...
2025.04
30.8
39.9
DPO + RMD
Base Model=LLAMA-3.2-3...
2025.04
28.9
36.5
DPO + RM
Base Model=LLAMA-3.2-3...
2025.04
27.8
39.9
DPO + RMC
Base Model=LLAMA-3.2-3...
2025.04
27.7
33.6
DPO + RMC
Base Model=LLAMA-3.2-3...
2025.04
25.2
30.3
Base
Base Model=LLAMA-3.2-3...
2025.04
23.6
21.1
Feedback
Search any
task
Search any
task