Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Block Infilling on SAFIM
Loading...
69.47
Pass@1
DeepSeek-R1
6.9452
23.1776
39.41
55.6424
Apr 18, 2026
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
DeepSeek-R1
Composition Level=L1
2026.04
69.47
QwQ-32B
Composition Level=L1
2026.04
48.9
DeepSeek-R1
Composition Level=L2
2026.04
17.38
DeepSeek-R1
Composition Level=L3
2026.04
16.24
QwQ-32B
Composition Level=L2
2026.04
12.92
QwQ-32B
Composition Level=L3
2026.04
9.35
Feedback
Search any
task
Search any
task