Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Python reference-model generation on RTLLM v2
Loading...
77.3
Pass@1
ChipMate-Python-9B
34.348
45.499
56.65
67.801
May 13, 2026
Pass@1
Pass@5
Updated 20d ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@5
ChipMate-Python-9B
Type=ChipMate-P, Size=9B
2026.05
77.3
81
ChipMate-Python-4B
Type=ChipMate-P, Size=4B
2026.05
75.3
80.1
DeepSeek R1
Type=Foundation Models...
2026.05
49.6
57.8
GPT-5.5
Type=Foundation Models...
2026.05
48.5
55.4
DeepSeek V4
Type=Foundation Models...
2026.05
44.4
54.3
CodeV-R1
Type=Specialized Model...
2026.05
42.7
51.8
DeepSeek Coder
Type=Foundation Models...
2026.05
42.4
50
Qwen3.5-9B
Type=Base Models, Size=9B
2026.05
40.1
51.8
Qwen3.5-4B
Type=Base Models, Size=4B
2026.05
38.2
46.1
CodeV-R1 (distill)
Type=Specialized Model...
2026.05
36
46.2
Feedback
Search any
task
Search any
task