Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Model Merging on Qwen3-4B-Base Transfer 8 benchmarks
Loading...
32.65
Math Accuracy
Pico
11.8396
17.2423
22.645
28.0477
Apr 18, 2026
Math Accuracy
Coding Accuracy
Finance Accuracy
Medical Accuracy
Overall Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Math Accuracy
Coding Accuracy
Finance Accuracy
Medical Accuracy
Overall Accuracy
Pico
Backbone=Qwen3-4B-Base
2026.04
32.65
58.25
65.45
65.94
55.57
KnOTS
Backbone=Qwen3-4B-Base
2026.04
26.22
55.93
61.13
56.61
49.97
DARE
Backbone=Qwen3-4B-Base
2026.04
26.07
57.18
61.67
55.39
50.08
DELLA
Backbone=Qwen3-4B-Base
2026.04
23.26
57.37
59.96
55.74
49.08
No Calibration
Backbone=Qwen3-4B-Base
2026.04
19.52
57.98
61.44
56.32
48.81
Core-TA
Backbone=Qwen3-4B-Base
2026.04
12.64
55.63
55.15
51.87
43.82
Feedback
Search any
task
Search any
task