Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Specification Synthesis on VERINA
Loading...
86.6
Pass@1
VERISPECGEN
12.968
32.084
51.2
70.316
Apr 12, 2026
Pass@1
Absolute Difference
Relative Difference
Updated 3mo ago
Evaluation Results
Method
Method
Links
Pass@1
Absolute Difference
Relative Difference
VERISPECGEN
Model=Claude Opus 4.5,...
2026.04
86.6
27.6
46.8
VERISPECGEN
Model=Claude Sonnet 4....
2026.04
72
21.3
42
VERISPECGEN
Model=Qwen3-Coder-480B...
2026.04
68.5
31.8
86.7
Baseline
Model=Claude Opus 4.5,...
2026.04
59
-
-
Baseline
Model=Claude Sonnet 4....
2026.04
50.7
-
-
VERISPECGEN
Model=Qwen3-Coder-30B-...
2026.04
50.3
21
71.7
Baseline
Model=Qwen3-Coder-480B...
2026.04
36.7
-
-
Baseline
Model=Qwen3-Coder-30B-...
2026.04
29.3
-
-
VERISPECGEN
Model=Qwen3-4B-Instruc...
2026.04
23
7.2
45.6
Baseline
Model=Qwen3-4B-Instruc...
2026.04
15.8
-
-
Feedback
Search any
task
Search any
task