List your company
ResearchFormerly WizWand

Language Modeling on NLP Benchmark Suite Aggregate

-9.2Average DeltaLoFIT
-9.532-7.291-5.05-2.809Feb 28, 2026
Updated 8mo ago

Evaluation results

MethodLinks
LoFITModel=Llama-3.1-8B, Params (%)=0.001%2026.02-9.2
JoLAModel=Llama-3.1-8B, Params (%)=0.003%2026.02-8.9
LoFITModel=Llama-3.2-1B, Params (%)=0.003%2026.02-7.3
JoLAModel=Llama-3.2-1B, Params (%)=0.007%2026.02-5.9
JoLAModel=gemma-3-1b, Params (%)=0.007%2026.02-5.5
Ours (1-vec)Model=gemma-3-1b, Params (%)=0.003%2026.02-4.7
LoFITModel=gemma-3-1b, Params (%)=0.003%2026.02-4.5
JoLAModel=Qwen 3 4B, Params (%)=0.007%2026.02-3.5
Ours (1-vec)Model=Qwen 3 4B, Params (%)=0.003%2026.02-3.4
Ours r=1Model=Llama-3.2-1B, Params (%)=0.005%2026.02-2.8
Ours (1-vec)Model=Llama-3.2-1B, Params (%)=0.003%2026.02-2.6
Ours r=1Model=Qwen 3 4B, Params (%)=0.005%2026.02-2.4
LoFITModel=Qwen 3 4B, Params (%)=0.003%2026.02-2.3
Ours (1-vec)Model=Llama-3.1-8B, Params (%)=0.001%2026.02-1.7
Ours r=1Model=gemma-3-1b, Params (%)=0.005%2026.02-1.5
Ours r=1Model=Llama-3.1-8B, Params (%)=0.003%2026.02-0.9