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

Multimodal Science Question Answering on ScienceQA

88.4Overall Average Score

Human

49.71259.75669.879.844Dec 3, 2025Dec 11, 2025Dec 20, 2025Dec 29, 2025Jan 7, 2026Jan 16, 2026Jan 25, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
88.490.2384.9787.4889.687.588.191.5982.42
85.4885.2681.5589.0983.2878.1991.588.1180.75
2025.12
83.9985.4872.4490.2782.6571.4992.8986.6679.04
2025.12
83.3884.4679.0884.6482.8975.8188.1583.8882.47
2025.12
82.6984.0673.4587.3681.8770.7590.7384.6979.1
2025.12
80.2577.5368.9585.3678.6866.3989.282.3177.76
2025.12
80.1580.1576.7282.8278.8972.5385.0282.8675.21
2025.12
79.9381.6270.648479.7770.886.6281.8676.53
2025.12
78.3779.6467.184.977.566587.9380.2574.85
2025.12
77.54--------
2025.12
76.84--------
76.8277.3173.4586.9174.0566.8687.9383.3771.85
2025.12
75.6274.5168.578.7375.9266.1981.9579.764.73
2025.12
75.1775.4470.8778.0974.6867.4379.9378.2369.68
2025.12
75.0876.7867.0478.0974.0566.1979.7278.0869.68
2025.12
74.7276.267.8377.2774.4965.7979.0277.7269.35
2025.12
74.17--------
2025.12
74.117176.0478.9166.4266.5381.8177.0668.82
2025.12
73.4773.9866.3778.1871.6564.379.6576.5168.03
2025.12
73.18--------
2026.01
69.5--------
2026.01
69.2--------
2026.01
69.2--------
2026.01
69--------
2026.01
68.9--------
2026.01
68.9--------
2026.01
68.8--------
2026.01
68.4--------
2026.01
68.4--------
2026.01
68.4--------
2026.01
67.2--------
2026.01
67.2--------
2026.01
62.2--------
2026.01
60.8--------
2026.01
60.2--------
2026.01
51.2--------