Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning Question Answering on ARC Challenge
Loading...
74.55
Accuracy
LoPT-GRPO
74.0404
74.1727
74.305
74.4373
May 6, 2026
Accuracy
Updated 27d ago
Evaluation Results
Method
Method
Links
Accuracy
LoPT-GRPO
Backbone=Qwen2.5-32B
2026.05
74.55
E2E-GRPO
Backbone=Qwen2.5-32B
2026.05
74.23
Base
Backbone=Qwen2.5-32B
2026.05
74.06
Feedback
Search any
task
Search any
task