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

Multi-disciplinary Reasoning on ScienceQA

69.83Accuracy

LLaVA-v1.5

65.545266.657667.7768.8824Oct 22, 2025
Updated 26d ago

Evaluation Results

MethodLinks
2025.10
69.83
2025.10
69.04
2025.10
68.84
2025.10
68.77
2025.10
68.51
2025.10
68.06
2025.10
67.28
2025.10
67.13
2025.10
66.21
2025.10
66.18
2025.10
66.1
2025.10
65.71