Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval base (Pass@1)
Loading...
82.3
Pass@1
SDAR-8B
17.612
34.406
51.2
67.994
Jun 4, 2026
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
SDAR-8B
Scale=8B, Tokens=55B,...
2026.06
82.3
SDAR-4B
Scale=4B, Tokens=55B,...
2026.06
76.8
Fast-dLLM-v2-7B
Scale=8B, Tokens=1B, F...
2026.06
63.4
OPDLM-8B
Scale=8B, Tokens=0.066...
2026.06
59.8
SDAR-1.7B
Scale=1.7B, Tokens=55B...
2026.06
59.8
Dream-7B
Scale=8B, Tokens=580B,...
2026.06
57.9
OPDLM-4B
Scale=4B, Tokens=0.076...
2026.06
56.1
Simple-dLLM
Scale=0.6B, Tokens=46B...
2026.06
45.7
Fast-dLLM-v2-1.5B
Scale=1.5B, Tokens=1B,...
2026.06
43.9
LLaDA-8B
Scale=8B, Tokens=1500B...
2026.06
35.4
OPDLM-1.7B
Scale=1.7B, Tokens=0.0...
2026.06
35.4
OPDLM-0.6B
Scale=0.6B, Tokens=0.0...
2026.06
20.1
Feedback
Search any
task
Search any
task