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

General AI Assistant Tasks on GAIA (Task success rate)

71.5Task Success Rate

PIVOT

29.940.751.562.3May 11, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
71.5
2026.05
68.5
2026.05
68.5
2026.05
66.7
2026.05
64.8
2026.05
64.2
2026.05
63.6
2026.05
60.6
2026.05
59.4
2026.05
57.6
2026.05
57
2026.05
56.4
2026.05
52.7
2026.05
51.5
2026.05
47.9
2026.05
44.8
2026.05
44.8
2026.05
41.8
2026.05
41.8
2026.05
41.8
2026.05
40.6
2026.05
40.6
2026.05
40
2026.05
37.6
2026.05
37.5
2026.05
37
2026.05
37
2026.05
35.2
2026.05
33.4
2026.05
31.5