List your company
ResearchFormerly WizWand

Reading Comprehension on BoolQ (val)

97.7AccuracyST-MOE
42.26856.65971.0585.441Jun 17, 2022Jan 26, 2023Sep 6, 2023Apr 17, 2024Nov 26, 2024Jul 7, 2025Feb 16, 2026
Updated 8mo ago

Evaluation results

MethodLinks
ST-MOEStatus=Fine-tuned SOTA2022.0697.7
PaLMStatus=Unified SOTA2022.0692.2
D2-LoRABackbone=Qwen2.5-7B-Instruct, Training Epochs=1, Scoring Method=CLL2026.0285.2
DoRABackbone=Qwen2.5-7B-Instruct, Training Epochs=1, Scoring Method=CLL2026.0284.2
LoRABackbone=Qwen2.5-7B-Instruct, Training Epochs=1, Scoring Method=CLL2026.0282
LLRCBackbone=Llama-2-13b, Param Ratio=0.80, Fine-tuning=None2025.1281.3
LLRCBackbone=Llama-2-13b, Param Ratio=0.90, Fine-tuning=None2025.1281.1
BaselineBackbone=Llama-2-13b, Param Ratio=1.00, Fine-tuning=None2025.1280.1
SVD-LLM+FinetuneBackbone=Llama-2-13b, Param Ratio=0.90, Fine-tuning=Alpaca2025.1280
UNIFIED-IO XLModel Size=XL2022.0679.7
SVD-LLM+FinetuneBackbone=Llama-2-13b, Param Ratio=0.80, Fine-tuning=Alpaca2025.1278.6
BaselineBackbone=Llama-2-7b, Param Ratio=1.00, Fine-tuning=None2025.1277.8
LLRCBackbone=Llama-2-7b, Param Ratio=0.90, Fine-tuning=None2025.1277.3
SVD-LLM (w)Backbone=Llama-2-13b, Param Ratio=0.90, Fine-tuning=None2025.1276.6
LLM-Pruner+FinetuneBackbone=Llama-2-13b, Param Ratio=0.90, Fine-tuning=Alpaca2025.1276.4
SVD-LLM (w)Backbone=Llama-2-13b, Param Ratio=0.80, Fine-tuning=None2025.1273.9
LLM-PrunerBackbone=Llama-2-13b, Param Ratio=0.90, Fine-tuning=None2025.1273.4
UNIFIED-IO LARGEModel Size=LARGE2022.0673.1
LLM-Pruner+FinetuneBackbone=Llama-2-13b, Param Ratio=0.80, Fine-tuning=Alpaca2025.1272.9
LLRCBackbone=Llama-2-7b, Param Ratio=0.80, Fine-tuning=None2025.1271.4
LLM-Pruner+FinetuneBackbone=Llama-2-7b, Param Ratio=0.90, Fine-tuning=Alpaca2025.1271.4
UNIFIED-IO BASEModel Size=BASE2022.0670.8
LLM-Pruner+FinetuneBackbone=Llama-2-7b, Param Ratio=0.80, Fine-tuning=Alpaca2025.1267.8
SVD-LLM+FinetuneBackbone=Llama-2-7b, Param Ratio=0.90, Fine-tuning=Alpaca2025.1267.6
SVD-LLM+FinetuneBackbone=Llama-2-7b, Param Ratio=0.80, Fine-tuning=Alpaca2025.1267.5
LLM-PrunerBackbone=Llama-2-13b, Param Ratio=0.80, Fine-tuning=None2025.1267.2
UNIFIED-IO SMALLModel Size=SMALL2022.0665.9
D2-LoRABackbone=Llama-3.2-3B-Instruct, Training Epochs=2, Scoring Method=CLL2026.0265.6
LLM-PrunerBackbone=Llama-2-7b, Param Ratio=0.90, Fine-tuning=None2025.1264.8
LLM-PrunerBackbone=Llama-2-7b, Param Ratio=0.80, Fine-tuning=None2025.1264.6
LoRABackbone=Llama-3.2-3B-Instruct, Training Epochs=2, Scoring Method=CLL2026.0262.6
DoRABackbone=Llama-3.2-3B-Instruct, Training Epochs=2, Scoring Method=CLL2026.0261.8
SVD-LLM (w)Backbone=Llama-2-7b, Param Ratio=0.90, Fine-tuning=None2025.1249
SVD-LLM (w)Backbone=Llama-2-7b, Param Ratio=0.80, Fine-tuning=None2025.1244.4