Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Task goal completion on AppWorld (test challenge)

32Goal Completion Score

RLOO

-0.8127.706516.22524.7435Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
32400.01
2026.03
32360
2026.03
30330
2026.03
28290.06
2026.03
2628-0.01
2026.03
2527-0.01
2026.03
2123-0.09
2026.03
1922-0.08
2026.03
0.610.71-0.18
2026.03
0.580.620.52
2026.03
0.540.630.03
2026.03
0.520.551.52
2026.03
0.510.51-0.07
2026.03
0.490.510.14
2026.03
0.460.49-0.29
2026.03
0.450.47-0.31