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

General Deep Research Tool Use on HLE

42.9Success Rate

Gemini-3-Pro

1.19612.02322.8533.677Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
42.9
2026.03
28.4
2026.03
26.9
2026.03
20.8
2026.03
19
2026.03
17.9
2026.03
17.8
2026.03
17.3
2026.03
13.8
2026.03
6.9
2026.03
6.4
2026.03
2.8