List your company

Math Reasoning on Minerva STEM evaluation

16.16AccuracyNaive Training
1.97445.65729.3413.0228Jul 21, 2025

Evaluation results

MethodLinks
Naive TrainingBackbone=LLaMA-DCLM, Reweighting Space=Data sources2025.0716.16
DataAgent_RLBackbone=LLaMA-DCLM, Reweighting Space=Data sources2025.0714.8
DataAgent_RLBackbone=LLaMA-FWE, Reweighting Space=Data sources2025.0713.46
DataAgent_SFTBackbone=LLaMA-DCLM, Reweighting Space=Data sources2025.0712.7
Naive TrainingBackbone=LLaMA-FWE, Reweighting Space=Data sources2025.0712.58
Naive TrainingBackbone=LLaMA-Nemo, Reweighting Space=Data sources2025.0712.3
DBLBackbone=LLaMA-DCLM, Reweighting Space=Data sources2025.0712.2
RegMixBackbone=LLaMA-FWE, Reweighting Space=Data sources2025.0712.2
DataAgent_SFTBackbone=LLaMA-FWE, Reweighting Space=Data sources2025.0712.19
DBLBackbone=LLaMA-FWE, Reweighting Space=Data sources2025.0712.05
RegMixBackbone=LLaMA-DCLM, Reweighting Space=Data sources2025.0711.5
DataAgent_RLBackbone=LLaMA-Nemo, Reweighting Space=Data sources2025.0710.83
DBLBackbone=LLaMA-Nemo, Reweighting Space=Data sources2025.0710.74
RegMixBackbone=LLaMA-Nemo, Reweighting Space=Data sources2025.0710.7
Naive TrainingBackbone=Pythia-1.4B, Reweighting Space=Data sources2025.0710.16
DataAgent_SFTBackbone=LLaMA-Nemo, Reweighting Space=Data sources2025.079.07
DataAgent_RLBackbone=Pythia-1.4B, Reweighting Space=Data sources2025.077.73
DataAgent_SFTBackbone=Pythia-1.4B, Reweighting Space=Data sources2025.077.19
RegMixBackbone=Pythia-1.4B, Reweighting Space=Data sources2025.076.92
Base ModelBackbone=LLaMA-Nemo, Reweighting Space=Data sources2025.074.85
Base ModelBackbone=Pythia-1.4B, Reweighting Space=Data sources2025.074.39
Base ModelBackbone=LLaMA-DCLM, Reweighting Space=Data sources2025.074.1
Base ModelBackbone=LLaMA-FWE, Reweighting Space=Data sources2025.072.52