Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generalization Performance Analysis on ID and OOD Evaluation Suite Combined
Loading...
80.2
Average Accuracy
ICR
49.312
57.331
65.35
73.369
Sep 26, 2025
Average Accuracy
Collapse Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
Collapse Count
ICR
Backbone=Qwen2.5-7B
2025.09
80.2
0
Few-shot*
Backbone=Qwen2.5-7B
2025.09
77.5
1
M²IV
Backbone=Qwen2.5-7B
2025.09
76.2
3
LIVE
Backbone=Qwen2.5-7B
2025.09
75.7
4
I2CL
Backbone=Qwen2.5-7B
2025.09
75.6
3
Zero-shot
Backbone=Qwen2.5-7B
2025.09
71.3
-
Few-shot*
Backbone=Llama2-7B
2025.09
66.8
1
ICR
Backbone=Llama2-7B
2025.09
59.9
0
M²IV
Backbone=Llama2-7B
2025.09
56.9
0
LIVE
Backbone=Llama2-7B
2025.09
56.6
2
I2CL
Backbone=Llama2-7B
2025.09
55
2
Zero-shot
Backbone=Llama2-7B
2025.09
50.5
-
Feedback
Search any
task
Search any
task