Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
App-based Agentic Task on AppWorld unseen tasks (test)
Loading...
66.6
Pass@1
SGE
47.048
52.124
57.2
62.276
Mar 2, 2026
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
SGE
RL Training=Strategy-G...
2026.03
66.6
GRPO
RL Training=GRPO, Aggr...
2026.03
49.3
Zero-Shot
Evaluation Protocol=Di...
2026.03
47.8
Feedback
Search any
task
Search any
task
