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

Science Question Answering on ScienceQA (test)

98.3Average Accuracy

Perceptio

82.065686.280390.49594.7097Feb 2, 2023Aug 11, 2023Feb 17, 2024Aug 25, 2024Mar 3, 2025Sep 9, 2025Mar 19, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.03
98.3------------------
2024.12
97.7------------------
2026.03
97.2------------------
2024.12
97.1------------------
2026.03
96.8------------------
2024.12
96------------------
2026.03
95.8------------------
2025.06
95.02-----------8.049.138.127.177.718.88-
2024.12
94.9------------------
2025.06
94.53-----------8.049.088.117.27.698.87-
2023.12
94.3995.296.2991.1894.4893.7593.1795.0493.21----------
2024.09
94.1------------------
2024.12
94------------------
2024.06
93.6395.7490.339295.592.4193.3193.9893.01----------
2023.12
93.1993.1296.6390.5592.5291.7792.2693.7292.22----------
2024.06
92.7894.9390.190.5594.5392.1292.293.8390.9----------
2023.12
92.7------------------
2023.04
92.5391.5696.7491.0990.6288.9993.5292.7392.16----------
2023.12
92.5391.5696.7491.0990.6288.9993.5292.7392.16----------
2024.01
92.03---93.8489.94-------------
2024.09
91.9------------------
2023.05
91.6895.918290.8295.2688.892.8992.4490.31----------
2023.04
91.6895.918290.8295.2688.892.8992.4490.31----------
2023.04
91.6895.918290.8295.2688.892.8992.4490.31----------
2023.12
91.6895.918290.8295.2688.892.8992.4490.31----------
2024.06
91.6895.918290.8295.2688.892.8992.4490.31----------
2024.01
91.68---95.2688.8-------------
2024.01
91.32---93.2189.24-------------
2023.04
90.9790.3695.588.5589.0587.891.0892.2288.73----------
2023.05
90.9290.3695.958889.498890.6690.9390.9----------
2023.04
90.9290.3695.958889.498890.6690.9390.9----------
2023.12
90.9290.3695.958889.498890.6690.9390.9----------
2023.11
90.9290.3695.958889.498890.6690.9390.9----------
2023.02
90.9290.3695.958889.498890.6690.9390.9----------
2024.06
90.9290.3695.958889.498890.6690.9390.9----------
2024.01
90.9---89.4988-------------
2023.05
90.8389.8894.4989.8288.9587.6191.8591.4589.72----------
2024.09
90.8------------------
2023.12
90.7------------------
2024.09
90.7------------------
2023.05
90.590.3294.3887.7389.4487.6590.3191.1989.26----------
2023.02
90.4591.0393.786.6490.1388.2589.4891.1289.26----------
2025.06
90.05-----------7.858.887.987.067.528.62-
2025.06
90.05-----------6.98.397.136.26.037.42-
2024.06
90.0389.8894.4989.8288.9587.6191.8591.4589.72----------
2025.03
89.9189.3996.0685.6488.7187.6588.590.9387.8----------
2024.09
89.8------------------
2024.09
89.6------------------
2025.11
89.5------------------
2025.03
89.4689.3993.3686.4588.5186.4789.3489.9888.53----------
2023.05
89.4189.2594.9485.2488.5187.4688.0890.1688.07----------
2024.06
89.4189.2594.9485.2488.5187.4688.0890.1688.07----------
2024.01
89.28---90.9687.32-------------
2025.03
88.9988.2895.1685.4587.3986.7188.0189.5488----------
2023.11
88.7888.593.0385.9188.5185.9788.1588.8888.6----------
2025.03
88.7389.1791.3485.3788.2785.5788.5789.3987.54----------
2025.11
88.5------------------
2024.06
88.4790.6785.3886.4590.9687.4687.3990.2785.23----------
2023.05
88.490.2384.9787.4889.687.588.191.5982.42----------
2023.04
88.490.2384.9787.4889.687.588.191.5982.42----------
2023.04
88.490.2384.9787.4889.687.588.191.5982.42----------
2023.12
88.490.2384.9787.4889.687.588.191.5982.42----------
2023.11
88.490.2384.9787.4889.687.588.191.5982.42----------
2023.02
88.490.2384.9787.4889.687.588.191.5982.42----------
2024.06
88.490.2384.9787.4889.687.588.191.5982.42----------
88.4---89.687.5-------------
2024.09
88.3------------------
88.3------------------
2025.11
87.98------------------
2024.09
87.6------------------
2023.04
86.5489.8374.1389.8288.2777.6492.1388.0383.72----------
86.5489.8374.1389.8288.2777.6492.1388.0383.72----------
2023.11
86.1184.594.1582.9188.3583.6488.7485.0585.6----------
2024.09
85.8------------------
2024.09
85.7------------------
2024.09
85.6------------------
2023.02
85.3184.0692.3582.1882.7582.7584.7485.7984.44----------
2023.05
85.1984.3788.384.3683.7280.3286.985.8384.05----------
2023.04
85.1984.3788.384.3685.7280.3286.985.8384.05----------
85.1984.3788.384.3683.7280.3286.985.8384.05----------
2023.12
85.1984.3788.384.3683.7280.3286.985.8384.05----------
2023.11
85.1984.3788.384.3683.7280.3286.985.8384.05----------
2023.02
85.1984.3788.384.3683.7280.3286.985.8384.05----------
2024.06
85.1984.3788.384.3683.7280.3286.985.8384.05----------
2024.01
85.19---83.7280.32-------------
2023.05
84.9187.5277.1785.8287.8882.986.8384.6585.37----------
2023.04
84.9187.5277.1785.8287.8882.986.8384.6585.37----------
2023.04
84.9187.5277.1785.8287.8882.986.8384.6585.37----------
2024.06
84.9187.5277.1785.8287.8882.986.8384.6585.37----------
2024.01
84.91---87.8882.9-------------
2023.04
83.9985.4872.4490.2782.6571.4992.8986.6679.04----------
2023.02
83.9985.4872.4490.2782.6571.4992.8986.6679.04----------
2024.01
83.99---82.6571.49-------------
2025.03
83.0583.6190.4475.9182.883.5479.5184.7380.03----------
2023.11
83.0279.7191.6882.8280.9483.2481.4683.7481.74----------
2023.05
82.6984.0673.4587.3681.8770.7590.7384.6979.1----------
2023.04
82.6984.0673.4587.3681.8770.7590.7384.6979.1----------
2023.12
82.6984.0673.4587.3681.8770.7590.7384.6979.1----------
2023.11
82.6984.0673.4587.3681.8770.7590.7384.6979.1----------
2024.06
82.6984.0673.4587.3681.8770.7590.7384.6979.1----------
Showing 100 of 283 rows