List your company
ResearchFormerly WizWand

Reading Comprehension on ARC-E

41.7AccuracyRegMix
29.32432.53735.7538.963Apr 9, 2026
Updated 6mo ago

Evaluation results

MethodLinks
RegMixBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0441.7
DoReMiBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0440.6
UniformBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0440
DOGEBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0440
DoGraphBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0439.2
Data Mixing LawBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0439
Dynamic Loss-BasedBackbone=LLaMA-1.1B, Pre-training Dataset=The Pile2026.0438.9
DoGraphBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0433.9
DoReMiBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0432.3
DoGraphModel=GPT-2 Small, Training Data=SlimPajama2026.0432.3
Data Mixing LawBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0432
Dynamic Loss-BasedModel=GPT-2 Small, Training Data=SlimPajama2026.0431.8
Dynamic Loss-BasedBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0431.7
RegMixBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0431.7
UniformBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0431.4
DOGEBackbone=GPT-2 Medium, Pre-training Dataset=SlimPajama2026.0431.3
DoReMiModel=GPT-2 Small, Training Data=SlimPajama2026.0430.9
DOGEModel=GPT-2 Small, Training Data=SlimPajama2026.0430.8
UniformModel=GPT-2 Small, Training Data=SlimPajama2026.0430.6
Data Mixing LawModel=GPT-2 Small, Training Data=SlimPajama2026.0430.1
RegMixModel=GPT-2 Small, Training Data=SlimPajama2026.0429.8