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

Tool Use on ToolUse

69.2Task Accuracy

GRPO

51.72856.26460.865.336May 12, 2026May 13, 2026May 14, 2026May 15, 2026May 16, 2026May 17, 2026May 18, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
69.2-------
2026.05
67.7-------
2026.05
66.9-------
2026.05
66.1-------
2026.05
66.1-------
2026.05
65.5-------
2026.05
64.3-------
2026.05
64.2-------
2026.05
63.7-------
2026.05
63.6-------
2026.05
63.3-------
2026.05
63.2-------
2026.05
61.6-------
2026.05
61-------
2026.05
57.3-------
2026.05
55.90.4681114.7-1,018--
2026.05
52.90.527-2.90.9761,248--
2026.05
52.4-------
2026.05
------53.2758.58
2026.05
------56.0260.89
2026.05
------55.9160.05
2026.05
------59.6361.58
2026.05
------62.0465.97
2026.05
------66.4468.61
2026.05
------64.6166.81