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

High-level Multimodal Reasoning on HLE-500

29.5Text Score

AutoAgent

3.0849.94216.823.658Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
29.523.928.2
2026.03
15.211.514.4
2026.03
14.72.712
2026.03
8.388.2
2026.03
84.47.2
2026.03
5.786.2
2026.03
4.92.74.4
2026.03
4.94.44.8
2026.03
4.75.34.8
2026.03
4.41.83.8
2026.03
4.12.73.8
2026.03
4.14.44.2