Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval (Accuracy (%), Avg.)
Loading...
58.54
Accuracy (%)
FP
4.6368
18.6309
32.625
46.6191
Jun 4, 2026
Accuracy (%)
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (%)
Average Score
FP
Model=Dream-Base, Quan...
2026.06
58.54
70.01
FP
Model=Dream-Instruct,...
2026.06
57.93
71.01
FAIR-Calib
Model=Dream-Instruct,...
2026.06
44.51
66.66
FAIR-Calib
Model=Dream-Base, Quan...
2026.06
41.46
64.64
FlatQuant
Model=Dream-Instruct,...
2026.06
41.46
63.98
FlatQuant
Model=Dream-Base, Quan...
2026.06
38.41
62.08
QuaRot
Model=Dream-Instruct,...
2026.06
32.32
61.14
QuaRot
Model=Dream-Base, Quan...
2026.06
23.17
57.49
RTN
Model=Dream-Instruct,...
2026.06
13.05
45.76
RTN
Model=Dream-Base, Quan...
2026.06
6.71
42
Feedback
Search any
task
Search any
task