List your company
ResearchFormerly WizWand

Knowledge on TruthfulQA 0-shot

63.85AccuracyUltraMix-187k
40.741246.740652.7458.7394Nov 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
UltraMix-187kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-187k2025.1163.85
UltraMix-190kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-190k2025.1163.32
UltraMix-170kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-170k2025.1161.45
UltraMixTraining Method=DPO, Dataset=UM-190k, Evaluation Protocol=0-shot2025.1160.57
TuluDPOTraining Method=DPO, Dataset=TuluDPO, Evaluation Protocol=0-shot2025.1160.28
UltraMixTraining Method=DPO, Dataset=UM-187k, Evaluation Protocol=0-shot2025.1160.25
UltraMixTraining Method=DPO, Dataset=UM-170k, Evaluation Protocol=0-shot2025.1159.05
ORPOTraining Method=ORPO, Dataset=ORPO, Evaluation Protocol=0-shot2025.1158.46
UltraMix-187kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-187k2025.1158.24
UltraMix-190kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-190k2025.1158
UltraMix-170kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-170k2025.1157.6
TuluDPOBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.1156.78
TuluDPOBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.1154.46
SmolLM-3-3B-SFTTraining Method=SFT, Evaluation Protocol=0-shot2025.1152.14
SFTBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=SFT2025.1151.64
CodePrefTraining Method=DPO, Dataset=CodePref, Evaluation Protocol=0-shot2025.1149.79
HelpSteerTraining Method=DPO, Dataset=HelpSteer, Evaluation Protocol=0-shot2025.1149.33
UltraFBTraining Method=DPO, Dataset=UltraFB, Evaluation Protocol=0-shot2025.1149.21
SFTBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=SFT2025.1146.84
UM-190kTraining Dataset=UM-190k2025.1144.86
UM-187kTraining Dataset=UM-187k2025.1144.63
UM-170kTraining Dataset=UM-170k2025.1144.51
TuluDPOTraining Dataset=TuluDPO2025.1144.4
ORPOTraining Dataset=ORPO2025.1144.34
HelpSteerTraining Dataset=HelpSteer2025.1143.75
UltraFBTraining Dataset=UltraFB2025.1143.67
SFTTraining Dataset=SFT2025.1142.07
CodePrefTraining Dataset=CodePref2025.1141.63