List your company

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

78.8MC STEM Average AccuracyQwen2 7B
47.80855.85463.971.946Dec 15, 2025Dec 16, 2025Dec 17, 2025

Evaluation results

MethodLinks
Qwen2 7BOpenness=Open-weight, Parameters=7B2025.1278.895.476.763.562.196.1
Qwen 2.5 7BOpenness=Open-weight, Parameters=7B2025.1274.793.467.660.356.695.4
Nemo-Nano 9BOpenness=Open-weight, Parameters=9B2025.1273.594.171.154.553.594.3
Gemma 2 9BOpenness=Open-weight, Parameters=9B2025.1272.892.762.858.955.494.4
MiMo 7BOpenness=Open-weight, Parameters=7B2025.1271.691.763.556.25393.5
Llama 3.1 8BOpenness=Open-weight, Parameters=8B2025.126986.455.756.553.792.7
Marin 8BOpenness=Fully-open, Parameters=8B2025.1268.189.258.152.747.393.2
Olmo 3 7BOpenness=Fully-open, Parameters=7B2025.1266.489.259.748.341.892.8
Olmo 3 7B# Parameters (incl. Embed)=7.30B2025.1266.389.259.548.24292.8
Apertus 8BOpenness=Fully-open, Parameters=8B2025.1266.387.952.451.747.691.9
Bolmo 7B# Parameters (incl. Embed)=7.63B2025.1265.588.55747.842.491.9
Granite 3.3 8BOpenness=Open-weight, Parameters=8B2025.126586.255.649.64390.8
OLMo 2 7BOpenness=Fully-open, Parameters=7B2025.1264.685.753.249.243.890.9
TFree-Hat 7B# Parameters (incl. Embed)=7.19B2025.1262.19055.251.520.593.3
Gaperon 8BOpenness=Fully-open, Parameters=8B2025.125877.243.144.536.888.4
EvaByte 6.5B# Parameters (incl. Embed)=6.49B2025.125474.244.337.927.286.6
BLT 7B# Parameters (incl. Embed)=10.55B2025.124965.541.637.622.577.8