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

General Deep Research Tool Use on GAIA (success rate)

80.3Success Rate

Gemini-3-Pro

20.08435.71751.3566.983Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
80.3
2026.03
66
2026.03
63.7
2026.03
61.2
2026.03
61
2026.03
60.2
2026.03
60
2026.03
50
2026.03
49.3
2026.03
25.8
2026.03
23.2
2026.03
22.4