Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dafny Program Verification on DafnyBench (test)
Loading...
89.1
Verification Rate (NoDiff)
SEVerA
67.884
73.392
78.9
84.408
Mar 26, 2026
Verification Rate (NoDiff)
Verification Rate
Violation Rate
Time (s)
Updated 23d ago
Evaluation Results
Method
Method
Links
Verification Rate (NoDiff)
Verification Rate
Violation Rate
Time (s)
SEVerA
constraints=NoDiff beh...
2026.03
89.1
89.1
0
25.6
DafnyBench baseline
2026.03
81.6
84
8.2
20.1
SEVerA (w/o constraints)
constraints=None
2026.03
79.2
84.8
7.9
18.4
LLM (Claude Sonnet 4.5)
Model=Claude Sonnet 4.5
2026.03
68.7
71.1
10.3
10.3
Feedback
Search any
task
Search any
task