List your company
ResearchFormerly WizWand

Knowledge on GPQA 0-shot

33.03ScoreUltraMix-190k
25.552427.493729.43531.3763Nov 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
UltraMix-190kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-190k2025.1133.03
UltraMix-187kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-187k2025.1132.78
UltraMixTraining Method=DPO, Dataset=UM-190k, Evaluation Protocol=0-shot2025.1132.03
UltraMix-190kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-190k2025.1131.87
UltraMix-170kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-170k2025.1131.63
UltraMix-187kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-187k2025.1131.46
UltraMixTraining Method=DPO, Dataset=UM-187k, Evaluation Protocol=0-shot2025.1131.42
TuluDPOBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.1131.29
SFTBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=SFT2025.1130.96
UltraMixTraining Method=DPO, Dataset=UM-170k, Evaluation Protocol=0-shot2025.1130.79
TuluDPOTraining Method=DPO, Dataset=TuluDPO, Evaluation Protocol=0-shot2025.1130.29
UltraMix-170kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-170k2025.1129.94
ORPOTraining Method=ORPO, Dataset=ORPO, Evaluation Protocol=0-shot2025.1129.78
UM-190kBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UM-190k2025.1129.78
UM-187kBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UM-187k2025.1129.68
TuluDPOBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.1129.61
UM-170kBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UM-170k2025.1128.61
SmolLM-3-3B-SFTTraining Method=SFT, Evaluation Protocol=0-shot2025.1128.57
SFTBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=SFT2025.1128.44
TuluDPOBase Model=OLMo-2-7B-SFT, DPO Training Dataset=TuluDPO2025.1127.93
ORPOBase Model=OLMo-2-7B-SFT, DPO Training Dataset=ORPO2025.1127.63
Instella-3B-SFT (UM-190k)DPO Training Dataset=UM-190k, Evaluation Protocol=0-shot2025.1127.46
Instella-3B-SFT (UM-187k)DPO Training Dataset=UM-187k, Evaluation Protocol=0-shot2025.1127.43
Instella-3B-SFT (UM-170k)DPO Training Dataset=UM-170k, Evaluation Protocol=0-shot2025.1127.35
UltraFBBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UltraFB2025.1127.27
SFTBase Model=OLMo-2-7B-SFT, DPO Training Dataset=SFT2025.1127.1
HelpSteerBase Model=OLMo-2-7B-SFT, DPO Training Dataset=HelpSteer2025.1127.1
Instella-3B-SFT (TuluDPO)DPO Training Dataset=TuluDPO, Evaluation Protocol=0-shot2025.1126.76
CodePrefBase Model=OLMo-2-7B-SFT, DPO Training Dataset=CodePref2025.1126.67
Instella-3B-SFT (ORPO)DPO Training Dataset=ORPO, Evaluation Protocol=0-shot2025.1126.43
Instella-3B-SFT (HelpSteer)DPO Training Dataset=HelpSteer, Evaluation Protocol=0-shot2025.1126.43
HelpSteerTraining Method=DPO, Dataset=HelpSteer, Evaluation Protocol=0-shot2025.1126.43
Instella-3B-SFT (CodePref)DPO Training Dataset=CodePref, Evaluation Protocol=0-shot2025.1126.1
Instella-3B-SFT (UltraFB)DPO Training Dataset=UltraFB, Evaluation Protocol=0-shot2025.1126.01
UltraFBTraining Method=DPO, Dataset=UltraFB, Evaluation Protocol=0-shot2025.1126.01
CodePrefTraining Method=DPO, Dataset=CodePref, Evaluation Protocol=0-shot2025.1126.01
Instella-3B-SFT (SFT)DPO Training Dataset=None (SFT Baseline), Evaluation Protocol=0-shot2025.1125.84