Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge Acquisition
Loading...
83.5
Task Accuracy
SFT
52.3
60.4
68.5
76.6
May 19, 2026
Task Accuracy
Updated 14d ago
Evaluation Results
Method
Method
Links
Task Accuracy
SFT
Model=Qwen3-4B
2026.05
83.5
L2 Reg
Model=Qwen3-4B
2026.05
83.5
FINCH
Model=Qwen3-4B
2026.05
83.3
WiSE-FT
Model=Qwen3-4B
2026.05
82.5
LoRA
Model=Qwen3-4B
2026.05
82.3
FLOW
Model=Qwen3-4B
2026.05
77.5
TALR
Model=Qwen3-4B
2026.05
62.5
DFT
Model=Qwen3-4B
2026.05
55.8
STM
Model=Qwen3-4B
2026.05
53.8
Base
Model=Qwen3-4B
2026.05
53.5
Feedback
Search any
task
Search any
task