Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generalization on Gen
Loading...
35.7
Gen Score
Modular Gradient Surgery
24.78
27.615
30.45
33.285
Feb 2, 2026
Gen Score
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Gen Score
Average Score
Modular Gradient Surgery
Backbone=Qwen-2.5-7B,...
2026.02
35.7
45
Math-Chat-IF
Backbone=Qwen-2.5-7B,...
2026.02
35.3
20.2
Global Surgery
Backbone=Qwen-2.5-7B,...
2026.02
34.9
43
Modular Gradient Surgery
Backbone=Llama-3.1-8B,...
2026.02
33.1
32.6
Normal Mixing
Backbone=Qwen-2.5-7B,...
2026.02
32.8
44.6
Chat-Math-IF
Backbone=Qwen-2.5-7B,...
2026.02
30.4
40.3
Global Surgery
Backbone=Llama-3.1-8B,...
2026.02
30.3
30.3
Normal Mixing
Backbone=Llama-3.1-8B,...
2026.02
25.2
27.3
Feedback
Search any
task
Search any
task