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

Web Agent Task Completion on HLE

37.6Accuracy

SlimSearcher (SFT+RL)

-0.5689.34119.2529.159Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
37.619.8211,418
2026.06
36.627.1612,936
35.823.9213,664
2026.06
34.923.9114,107
2026.06
29.824.8611,924
2026.06
27.819.5111,497
2026.06
26.6--
2026.06
25.927.8613,169
2026.06
24.9--
2026.06
20.3--
2026.06
19.97.452,960
2026.06
14.65.172,349
2026.06
11.615.526,579
2026.06
6132,713
2026.06
0.925.772,570