Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Conditional Likelihood Estimation on GPQA
Loading...
30.4
Accuracy
LLaMA-3-8B
19.896
22.623
25.35
28.077
Mar 3, 2026
Accuracy
Number of Function Evaluations (NFE)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Number of Function Evaluations (NFE)
LLaMA-3-8B
Estimation method=prob...
2026.03
30.4
1
LLaDA-Instruct-8B
Estimation method=DiSE
2026.03
30.1
1
LLaDA-1.5-8B
Estimation method=DiSE
2026.03
29.9
1
LLaDA-Instruct-8B
Estimation method=MC,...
2026.03
28.6
32
LLaDA-1.5-8B
Estimation method=MC,...
2026.03
27.5
32
LLaDA-Instruct-8B
Estimation method=MC,...
2026.03
21.2
1
LLaDA-1.5-8B
Estimation method=MC,...
2026.03
20.3
1
Feedback
Search any
task
Search any
task