Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Capability on ARC-c OpenR1-Math Harder
Loading...
70.6
Accuracy
RePO
32.12
42.11
52.1
62.09
Feb 11, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
RePO
Backbone=Qwen, Paramet...
2026.02
70.6
Qwen-4B
Backbone=Qwen, Paramet...
2026.02
62.4
LUFFY
Backbone=Qwen, Paramet...
2026.02
33.6
Feedback
Search any
task
Search any
task