Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
RTL Generation on RTLLM VerilogEval CVDP Combined v2
Loading...
94
Mean Z-score Pass@10
GPT-OSS-120B
-211.76
-132.38
-53
26.38
Jun 11, 2026
Mean Z-score Pass@10
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Z-score Pass@10
GPT-OSS-120B
Role=Teacher, SFT=null...
2026.06
94
STG
Role=Fine-tuned, Base...
2026.06
77
STG
Role=Fine-tuned, Base...
2026.06
68
STG
Role=Fine-tuned, Base...
2026.06
56
CodeV-R1
Role=Fine-tuned, Base...
2026.06
54
SiliconMind-V1
Role=Fine-tuned, Base...
2026.06
46
SiliconMind-V1
Role=Fine-tuned, Base...
2026.06
37
SiliconMind-V1
Role=Fine-tuned, Base...
2026.06
30
VeriRL (reproduced)
Role=Fine-tuned, Base...
2026.06
-29
Qwen3-8B
Role=Base, SFT=null, R...
2026.06
-80
Qwen2.5-C-7B-Instruct
Role=Base, SFT=null, R...
2026.06
-151
Qwen3-4B-Thinking
Role=Base, SFT=null, R...
2026.06
-200
Feedback
Search any
task
Search any
task