List your company

Science Question Answering on ARC Easy (Character-level Accuracy)

87.8Accuracy (Character-level)No pruning
24.77641.13857.573.862Mar 16, 2026Mar 17, 2026Mar 19, 2026Mar 20, 2026Mar 22, 2026Mar 23, 2026Mar 25, 2026

Evaluation results

MethodLinks
No pruningSparsity=0, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0387.8
Magnitude-DimSparsity=10%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0380.2
DIETSparsity=10%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0379.1
LFM2 1.2BParameter Count=1.2B, Evaluation Protocol=0-shot2026.0377.9
Nemotron-Flash 1BParameter Count=1B, Evaluation Protocol=0-shot2026.0374.83
LFM2 700MParameter Count=700M, Evaluation Protocol=0-shot2026.0374.6
Gemma3 1BParameter Count=1B, Evaluation Protocol=0-shot2026.0373
MobileLLM-Flash 1.4BParameter Count=1.4B, Evaluation Protocol=0-shot2026.0372.26
MobileLLM-Flash 650MParameter Count=650M, Evaluation Protocol=0-shot2026.0366.55
LFM2 350MParameter Count=350M, Evaluation Protocol=0-shot2026.0366.04
Llama3.2 1BParameter Count=1B, Evaluation Protocol=0-shot2026.0363.47
MobileLLM-Flash 350MParameter Count=350M, Evaluation Protocol=0-shot2026.0363.26
Magnitude-DimSparsity=20%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0362
DIETSparsity=20%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0361.7
Qwen3 0.6BParameter Count=0.6B, Evaluation Protocol=0-shot2026.0358.08
Gemma3 270MParameter Count=270M, Evaluation Protocol=0-shot2026.0357.32
PuDDingSparsity=20%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0351.3
PuDDingSparsity=10%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0349.1
SliceGPTSparsity=20%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0327.4
SliceGPTSparsity=10%, Backbone=Gemma-2 9B, Evaluation Protocol=Zero-shot2026.0327.2