Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Task Solving on AppWorld (test-n)
Loading...
81.15
TGC Average
CLEAR
71.6548
74.1199
76.585
79.0501
Apr 8, 2026
TGC Average
TGC Pass@3
SGC Average
SGC Pass@3
Updated 9d ago
Evaluation Results
Method
Method
Links
TGC Average
TGC Pass@3
SGC Average
SGC Pass@3
CLEAR
Model for πE=Claude-So...
2026.04
81.15
91.67
66.67
82.14
ACE
Model for πE=Claude-So...
2026.04
74.4
85.71
58.93
73.21
Baseline
Model for πE=Claude-So...
2026.04
72.62
86.9
52.38
66.07
RAG
Model for πE=Claude-So...
2026.04
72.02
86.31
54.67
71.43
Feedback
Search any
task
Search any
task