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

STEM & Puzzle on ScienceQA (test)

97.5Accuracy

MMFineReason-8B

94.27695.11395.9596.787Jan 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
97.5
2026.01
97.2
2026.01
97.1
2026.01
96.9
2026.01
96.8
2026.01
96.4
2026.01
95.8
2026.01
95.4
2026.01
95.2
2026.01
94.8
2026.01
94.4