Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
RTL Design Code Generation on VerilogHuman v1
Loading...
99.3
Syntax Accuracy
Claude-3.7
51.356
63.803
76.25
88.697
May 15, 2026
Syntax Accuracy
Function Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Syntax Accuracy
Function Accuracy
Claude-3.7
Evaluation Protocol=RT...
2026.05
99.3
79.8
GPT-4o
Evaluation Protocol=RT...
2026.05
98.7
71.1
Claude-3.7
Evaluation Protocol=Or...
2026.05
98.1
80.1
GPT-4o
Evaluation Protocol=Or...
2026.05
96.8
67.3
GPT-4o-mini
Evaluation Protocol=Or...
2026.05
89.1
51.3
LlaMA-70B
Evaluation Protocol=Or...
2026.05
78.8
47.4
LlaMA-405B
Evaluation Protocol=Or...
2026.05
75
48.7
GPT-3.5
Evaluation Protocol=Or...
2026.05
73.7
32.7
QwQ-32B
Evaluation Protocol=Or...
2026.05
53.2
44.2
Feedback
Search any
task
Search any
task