Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on MBPP (Positive seeds, Mean Δ, Std. Δ)
Loading...
5
Positive Seeds Count
TALAN
4.75
4.875
5
5.125
Jun 5, 2026
Positive Seeds Count
Mean Delta
Std. Delta
Updated 1mo ago
Evaluation Results
Method
Method
Links
Positive Seeds Count
Mean Delta
Std. Delta
TALAN
Backbone=Llama-3.2-1B,...
2026.06
5
1.34
3.04
TALAN
Backbone=Llama-3.2-1B,...
2026.06
5
0.6
0.58
Feedback
Search any
task
Search any
task
