List your company

Multiple Choice STEM Question Answering on OlmoBaseEval MCSTEM

83.4MCSTEM ScoreSeed 36B
35.0447.59560.1572.705Dec 15, 2025Jan 2, 2026Jan 20, 2026Feb 7, 2026Feb 25, 2026Mar 15, 2026Apr 3, 2026

Evaluation results

MethodLinks
Seed 36BModel Category=Open-weight, Number of Parameters=36B2025.1283.497.382.869.670.197.1
Qwen 2.5 32BModel Category=Open-weight, Number of Parameters=32B2025.1282.29779.768.868.497.1
Mistral 3.1 24BModel Category=Open-weight, Number of Parameters=24B2025.1281.596.276.168.870.496.3
Gemma 3 27BModel Category=Open-weight, Number of Parameters=27B2025.1280.295.874.964.768.796.8
Llama 3.1 70BModel Category=Open-weight, Number of Parameters=70B2025.1280.195.27067.872.395.4
Qwen 3# Parameters=8B, # Train Tokens=36T, Train Compute (10^23 FLOPs)=17.32026.0478.795.476.763.56296
Nemo. 3 Nano# Parameters=30B A3B, # Train Tokens=25T, Train Compute (10^23 FLOPs)=5.42026.0478.694.873.864.264.995
Kimi Linear# Parameters=48B A3B, # Train Tokens=6T, Train Compute (10^23 FLOPs)=1.02026.0477.594.367.864.666.694
Marin 32BModel Category=Fully-open, Number of Parameters=32B2025.1275.993.468.461.860.895.1
Falcon H1# Parameters=7B, # Train Tokens=12T, Train Compute (10^23 FLOPs)=5.52026.0475.794.273.859.955.994.7
LLM 360 K2V2 70BModel Category=Fully-open, Number of Parameters=70B2025.1275.69364.763.761.495.3
Gemma 2 27BModel Category=Open-weight, Number of Parameters=27B2025.1275.694.165.861.86195.1
OLMo 2 32BModel Category=Fully-open, Number of Parameters=32B2025.1275.394.464.760.262.295.1
Olmo 3 32BModel Category=Fully-open, Number of Parameters=32B2025.1274.594.770.857.653.895.5
Nemotron-H# Parameters=8B, # Train Tokens=15T, Train Compute (10^23 FLOPs)=7.22026.0472.493.364.256.254.594.1
Apertus 70BModel Category=Fully-open, Number of Parameters=70B2025.127090.757.855.952.493.3
Olmo Hybrid# Parameters=7B, # Train Tokens=6T, Train Compute (10^23 FLOPs)=2.6, Decoding Settings=--disable-cascade-attn, --enforce-eager2026.047090.864.652.148.793.9
Olmo 3# Parameters=7B, # Train Tokens=6T, Train Compute (10^23 FLOPs)=2.6, Decoding Settings=--disable-cascade-attn, --enforce-eager2026.0466.289.259.74841.692.8
Falcon Mamba# Parameters=7B, # Train Tokens=6T, Train Compute (10^23 FLOPs)=2.52026.0464.285.75248.942.591.9
Recurr. Gemma# Parameters=9B, # Train Tokens=2T, Train Compute (10^23 FLOPs)=1.02026.0461.682.649.647.339.488.9
Gaperon 24BModel Category=Fully-open, Number of Parameters=24B2025.1256.272.745.342.635.484.9
xLSTM# Parameters=7B, # Train Tokens=2T, Train Compute (10^23 FLOPs)=0.92026.0436.946.734.331.423.248.8