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

Web Agent on WebArena

35.8Success Rate

w/o Attack

1.37610.31319.2528.187May 19, 2026May 24, 2026May 30, 2026Jun 5, 2026Jun 11, 2026Jun 17, 2026Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
35.8--
2026.05
33.3--
2026.05
31.9--
2026.05
31.7--
2026.05
30.8--
2026.05
30.2--
2026.06
29.4--
2026.05
27.2--
2026.06
26.5--
2026.05
26.1--
2026.06
26.1--
2026.06
24.9--
2026.05
24.3--
2026.05
24.1--
2026.05
23.8--
2026.05
23.5--
2026.06
23.2--
2026.06
22.8--
2026.05
22.7--
2026.06
20.4520.26140.0284
2026.06
20.4519.90910.0398
2026.06
20.4520.28410.017
2026.06
19.7--
2026.05
19.6--
2026.05
19.2--
2026.05
18.4--
2026.06
18.4--
2026.05
18.2--
2026.06
18.1821.9886-0.0511
2026.06
18.1820.4205-0.0341
2026.05
18.1--
2026.05
18--
2026.06
17.6--
2026.05
17.5--
2026.05
16.6--
2026.06
16.4--
2026.06
15.7--
2026.06
15.3--
2026.06
15.1--
2026.06
14.6--
2026.05
14.5--
2026.05
13.4--
2026.05
12.7--
2026.06
12.4--
2026.05
9.5--
2026.05
8.7--
2026.05
8.6--
2026.05
8.1--
2026.05
7.8--
2026.05
5.5--
2026.05
5.2--
2026.05
5.2--
2026.05
4.8--
2026.05
4.7--
2026.05
4.3--
2026.05
2.7--