Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Aggregate Performance Evaluation on Average SST2, AGNEWS, GSM8K
Loading...
26.47
HS Score
SFT
-0.31
6.6425
13.595
20.5475
Feb 28, 2026
HS Score
FA Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
HS Score
FA Score
SFT
Backbone=Qwen-2-7B
2026.02
26.47
81.25
Vaccine
Backbone=Qwen-2-7B
2026.02
25.54
80.12
Lisa
Backbone=Qwen-2-7B
2026.02
12.54
80.61
Antibody
Model=Gemma-2-9B
2026.02
4.71
79.16
Booster
Backbone=Qwen-2-7B
2026.02
3.21
82.65
Booster + Lisa
Model=Gemma-2-9B
2026.02
2.72
78.71
Booster + Lisa
Model=Llama-2-7B
2026.02
1.84
62.57
Booster + Lisa
Model=Qwen-2-7B
2026.02
1.67
82.98
Antibody
Model=Llama-2-7B
2026.02
1.32
65.24
Antibody
Backbone=Qwen-2-7B
2026.02
0.72
82.95
Antibody
Model=Qwen-2-7B
2026.02
0.72
82.95
Feedback
Search any
task
Search any
task