Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Degree of Change on PerturbQA K562
Loading...
88.32
Accuracy
BoN w/ Full Set
80.0416
82.1908
84.34
86.4892
Mar 9, 2026
Accuracy
Updated 2mo ago
Evaluation Results
Method
Method
Links
Accuracy
BoN w/ Full Set
Decoding Strategy=Best...
2026.03
88.32
Majority Voting
Decoding Strategy=Majo...
2026.03
85.1
BoN w/ Qwen-PRM800K
Decoding Strategy=Best...
2026.03
84.87
Greedy Decoding
Decoding Strategy=Greedy
2026.03
83.47
BoN w/ Llama-PRM800K
Decoding Strategy=Best...
2026.03
82.84
BoN w/ VersaPRM
Decoding Strategy=Best...
2026.03
80.36
Feedback
Search any
task
Search any
task