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

Multi-turn Agent Task on Search-QA

50.49Success Rate

GRPO

13.060422.777732.49542.2123Jun 26, 2026Jun 27, 2026Jun 28, 2026Jun 29, 2026Jun 30, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.06
50.492.65
2026.06
49.122.62
2026.06
48.932.69
2026.06
48.582.61
2026.06
48.392.57
2026.06
48.192.51
2026.06
48.192.51
2026.06
48.1-
2026.06
47.82.59
2026.06
46.4-
2026.06
45.212.64
2026.06
45.022.74
2026.06
45-
2026.06
44.732.66
2026.06
44.432.69
2026.06
43.3-
2026.06
42.332.77
2026.06
42.3-
2026.06
42.242.67
2026.06
42.042.67
2026.06
41.992.64
2026.06
41.462.77
2026.06
41.1-
2026.06
40.2-
2026.06
40.192.81
2026.06
39.62.43
2026.06
39.4-
2026.06
39.362.69
2026.06
32.711.77
2026.06
31.152.09
2026.06
14.51.57