Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
RTL – Code Improvement (Linting / QoR) on CVDP non-agentic 1.0
Loading...
51.25
Pass@1
DeepSeek-R1
17.45
26.225
35
43.775
Dec 4, 2025
Pass@1
Updated 3mo ago
Evaluation Results
Method
Method
Links
Pass@1
DeepSeek-R1
mode=agentic framework
2025.12
51.25
Granite-4
mode=agentic framework
2025.12
48.75
GPT-o4 Mini
mode=agentic framework
2025.12
44.74
GPT-o4 Mini
mode=single-shot
2025.12
41
Nemotron-Mini
mode=agentic framework
2025.12
36
SmolLM
mode=agentic framework
2025.12
30
DeepSeek-R1
mode=single-shot
2025.12
21.25
Granite-4
mode=single-shot
2025.12
20.51
Nemotron-Mini
mode=single-shot
2025.12
20
SmolLM
mode=single-shot
2025.12
18.75
Feedback
Search any
task
Search any
task