List your company
ResearchFormerly WizWand

Leaderboard Evaluation on Open LLM Leaderboard 1

69.28Overall ScoreUltraMix-190k
48.58453.95759.3364.703Nov 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
UltraMix-190kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-190k2025.1169.28
UltraMix-187kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-187k2025.1168.97
UltraMix-190kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-190k2025.1168.5
UltraMix-170kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-170k2025.1168.29
UltraMix-187kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-187k2025.1167.95
UltraMix-170kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-170k2025.1166.79
TuluDPOBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.1166.73
TuluDPOBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.1166.3
SFTBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=SFT2025.1164.76
UM-190kBackbone=Apertus-8B-SFT2025.1163.83
UM-187kBackbone=Apertus-8B-SFT2025.1163.43
SFTBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=SFT2025.1162.85
UltraMixTraining Method=DPO, Dataset=UM-190k2025.1162.51
UltraMixTraining Method=DPO, Dataset=UM-187k2025.1162.29
UM-170kBackbone=Apertus-8B-SFT2025.1162.26
Instella-3B-SFT (UM-190k)DPO Training Dataset=UM-190k2025.1162.03
Instella-3B-SFT (UM-187k)DPO Training Dataset=UM-187k2025.1161.78
TuluDPOTraining Method=DPO, Dataset=TuluDPO2025.1161.67
TuluDPOBackbone=Apertus-8B-SFT2025.1161.67
Instella-3B-SFT (UM-170k)DPO Training Dataset=UM-170k2025.1161.28
UltraMixTraining Method=DPO, Dataset=UM-170k2025.1161.19
Instella-3B-SFT (TuluDPO)DPO Training Dataset=TuluDPO2025.1160.96
UltraFBBackbone=Apertus-8B-SFT2025.1160.94
ORPOBackbone=Apertus-8B-SFT2025.1160.58
Instella-3B-SFT (ORPO)DPO Training Dataset=ORPO2025.1160.32
Instella-3B-SFT (UltraFB)DPO Training Dataset=UltraFB2025.1159.99
ORPOTraining Method=ORPO, Dataset=ORPO2025.1159.89
Instella-3B-SFT (HelpSteer)DPO Training Dataset=HelpSteer2025.1159.76
Instella-3B-SFT (SFT)DPO Training Dataset=None (SFT Baseline)2025.1159.62
SFTBackbone=Apertus-8B-SFT2025.1159.49
HelpSteerBackbone=Apertus-8B-SFT2025.1159.44
Instella-3B-SFT (CodePref)DPO Training Dataset=CodePref2025.1158.39
SmolLM-3-3B-SFTTraining Method=SFT2025.1157.48
HelpSteerTraining Method=DPO, Dataset=HelpSteer2025.1157.17
CodePrefBackbone=Apertus-8B-SFT2025.1156.7
UltraFBTraining Method=DPO, Dataset=UltraFB2025.1156.5
CodePrefTraining Method=DPO, Dataset=CodePref2025.1155.33
UM-190k2025.1153.95
UM-187k2025.1153.53
TuluDPO2025.1152.57
ORPO2025.1152.33
UM-170k2025.1152
UltraFB2025.1150.95
SFT2025.1150.73
HelpSteer2025.1150.68
CodePref2025.1149.38