Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Formal Specification Synthesis on VERINA SpecGen (test)
Loading...
30.3
Pass@1
SFT No-Test
14.076
18.288
22.5
26.712
Apr 12, 2026
Pass@1
Updated 3mo ago
Evaluation Results
Method
Method
Links
Pass@1
SFT No-Test
Model variant=SFT No-Test
2026.04
30.3
Merged (α=0.2)
Model variant=Merged (...
2026.04
15.6
Qwen3-4B-Instruct-2507
Model variant=Base Model
2026.04
14.7
Feedback
Search any
task
Search any
task