Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cross-domain Generalization on Cross-Domain Summary Code Scientific Agentic tool
Loading...
70
Average Score
DASD
68.024
68.537
69.05
69.563
May 21, 2026
Average Score
Updated 12d ago
Evaluation Results
Method
Method
Links
Average Score
DASD
Backbone=Qwen3-8B
2026.05
70
GRPO
Backbone=Qwen3-8B
2026.05
68.5
Qwen3-8B
Post-training=Base
2026.05
68.1
OPSD
Backbone=Qwen3-8B
2026.05
68.1
Feedback
Search any
task
Search any
task