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

Multiple Choice Question Answering on Bolmo Evaluation Suite MC STEM 7B

78.8MC STEM Average Accuracy

Qwen2 7B

47.80855.85463.971.946Dec 15, 2025Dec 16, 2025Dec 17, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
78.895.476.763.562.196.1
2025.12
74.793.467.660.356.695.4
2025.12
73.594.171.154.553.594.3
2025.12
72.892.762.858.955.494.4
2025.12
71.691.763.556.25393.5
2025.12
6986.455.756.553.792.7
2025.12
68.189.258.152.747.393.2
2025.12
66.489.259.748.341.892.8
2025.12
66.389.259.548.24292.8
2025.12
66.387.952.451.747.691.9
2025.12
65.588.55747.842.491.9
2025.12
6586.255.649.64390.8
2025.12
64.685.753.249.243.890.9
2025.12
62.19055.251.520.593.3
2025.12
5877.243.144.536.888.4
2025.12
5474.244.337.927.286.6
2025.12
4965.541.637.622.577.8