Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Closed-Book Question Answering on ARC-c (EM)
Loading...
85.9
EM
Base
30.884
45.167
59.45
73.733
Nov 10, 2025
EM
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
Base
Backbone=Qwen-2.5-7B
2025.11
85.9
LOGO (Entropy)
Backbone=LLaMA-3.1-8B
2025.11
69.9
Base
Backbone=LLaMA-3.1-8B
2025.11
64.7
LOGO (Norm)
Backbone=DeepSeek-LLM-...
2025.11
33
Feedback
Search any
task
Search any
task