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

Science Question Answering on ScienceQA (Component Metrics)

88.6IMG Score

Qwen2.5-VL-7B-Instruct

-3.12716820.68661644.500468.314184Dec 5, 2025Dec 20, 2025Jan 4, 2026Jan 20, 2026Feb 4, 2026Feb 19, 2026Mar 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
88.6--------
2026.02
88.5--------
2026.03
87.590.2384.9787.4889.688.191.5982.4288.4
2026.03
87.4192.5894.8392.2781.2397.2887.6786.8292.97
2026.02
86.7--------
2026.02
85.7--------
2026.03
80.7687.6189.4395.9186.0797.6390.8684.1190.14
2026.03
78.7886.598290.3683.6392.488.6681.0286.61
2026.03
78.7383.780.3191.9182.8489.286.7184.0585.12
2026.02
76.9--------
2026.02
76.9--------
2026.03
74.1785.6175.9390.2784.492.3385.7982.9884.77
2026.03
73.1884.1575.1487.6482.9989.6984.480.9583.16
2026.02
72.8--------
2026.02
72.8--------
2026.03
72.5380.1576.7282.8278.8985.0282.8675.2180.15
2026.02
71.8--------
2026.02
71.6--------
2026.03
71.4985.4872.4490.2782.6592.8986.6679.0483.99
2026.02
71.3--------
2026.03
70.881.6270.648479.7786.6281.8676.5379.93
2026.03
70.7584.0673.4587.3681.8790.7384.6979.182.69
2026.02
69.7--------
2026.02
69.4--------
2026.02
69.2--------
2026.02
69--------
2026.02
68.8--------
2026.02
68.6--------
2026.02
68.2--------
2026.03
67.4375.4470.8778.0974.6879.9378.2369.6875.17
2026.02
67.3--------
2026.02
67.1--------
2026.02
66.8--------
2026.02
66.6--------
2026.03
66.537176.0478.9166.4281.8177.0668.8274.11
2026.03
65.7976.267.8377.2774.4979.0277.7269.3574.72
2026.03
6579.6467.184.977.5687.9380.2574.8578.37
2025.12
0.92760.93070.96740.87090.92420.89270.92910.91170.9229
2025.12
0.90480.92720.87850.89910.92720.91290.91450.90110.9097
2025.12
0.90330.91520.91450.92450.91940.92260.92110.9110.9175
2025.12
0.89690.91790.94260.89640.9140.91010.92840.89780.9175
2025.12
0.8830.91870.84590.930.92280.92750.90640.90640.9064
2025.12
0.880.90360.95950.880.89490.90660.90930.9090.9092
2025.12
0.8750.90230.84970.87480.8960.8810.91590.82420.884
2025.12
0.87460.89250.94940.85240.88510.88080.90160.88070.8941
2025.12
0.83340.88720.86840.84910.87590.88080.88580.8510.8734
2025.12
0.82750.84060.92350.82180.82750.84740.85790.84440.8531
2025.12
0.80320.84370.8830.84360.83720.8690.85830.84050.8519
2025.12
0.77640.89830.74130.89820.88270.92130.88030.83720.8654
2025.12
0.71490.85480.72440.90270.82650.92890.86660.79040.8399
2025.12
0.7080.81620.70640.840.79770.86620.81860.76530.7993
2025.12
0.67920.78820.70980.83180.77370.86130.80720.74030.7831
2025.12
0.67430.75440.70870.78090.74680.79930.78230.69680.7517
2025.12
0.67280.74640.69740.760.74440.77420.7680.68890.7397
2025.12
0.66530.710.76040.78910.66420.81810.77060.68820.7411
2025.12
0.62170.59330.69180.61180.62710.58540.62960.59920.6187
2025.12
0.61380.60480.63890.60270.6320.570.60720.6190.6114
2025.12
0.61380.68160.69180.74910.63780.77840.72980.650.7012
2025.12
0.55280.65190.46790.65550.66960.64950.58040.6750.6142
2025.12
0.54880.5950.54330.61820.6290.59790.57270.62160.5902
2025.12
0.54490.64030.48820.63550.65880.64110.57120.67170.6072
2025.12
0.5260.60880.46570.66640.62610.65510.56830.63940.5937
2025.12
0.51170.56080.46230.58090.59430.5540.51650.59720.5454
2025.12
0.40080.40280.46130.29250.47450.33660.39350.40670.3983
2026.03
--------86.32
2026.03
--------77.54
2026.03
--------74.17
2026.03
--------76.84
2026.03
--------73.18