List your company
ResearchFormerly WizWand

Evaluation on Overall Performance

85.18Average ScoreLD-MoLE
41.86453.109564.35575.6005Sep 30, 2025Oct 7, 2025Oct 15, 2025Oct 22, 2025Oct 30, 2025Nov 6, 2025Nov 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
LD-MoLEModel=Llama3.1-8B, TP=2.33 %2025.0985.18
ReMoLEModel=Llama3.1-8B, TP=2.17 %2025.0984.47
MoLA(2468)Model=Llama3.1-8B, TP=1.26 %2025.0982.85
MoLA(8888)Model=Llama3.1-8B, TP=2.17 %2025.0982.48
LD-MoLEModel=Llama3.2-3B, TP=3.28 %2025.0982.05
LD-MoLEModel=Qwen3-1.7B, TP=4.23 %2025.0981.63
ReMoLEModel=Llama3.2-3B, TP=3.11 %2025.0981.42
ReMoLEModel=Qwen3-1.7B, TP=4.12 %2025.0981.02
MoLA(2468)Model=Qwen3-1.7B, TP=2.39 %2025.0979.28
MoLA(8888)Model=Qwen3-1.7B, TP=4.12 %2025.0979.24
MoLA(2468)Model=Llama3.2-3B, TP=1.80 %2025.0978.72
MoLA(8888)Model=Llama3.2-3B, TP=3.11 %2025.0978.18
UM-190kBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UM-190k2025.1150.02
UM-187kBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UM-187k2025.1149.8
UM-170kBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UM-170k2025.1149.14
TuluDPOBase Model=OLMo-2-7B-SFT, DPO Training Dataset=TuluDPO2025.1148.27
ORPOBase Model=OLMo-2-7B-SFT, DPO Training Dataset=ORPO2025.1147.26
UltraFBBase Model=OLMo-2-7B-SFT, DPO Training Dataset=UltraFB2025.1147.08
Instella-3B-SFT (UM-190k)DPO Training Dataset=UM-190k2025.1146.88
Instella-3B-SFT (UM-187k)DPO Training Dataset=UM-187k2025.1146.58
CodePrefBase Model=OLMo-2-7B-SFT, DPO Training Dataset=CodePref2025.1146.51
Instella-3B-SFT (UM-170k)DPO Training Dataset=UM-170k2025.1145.95
HelpSteerBase Model=OLMo-2-7B-SFT, DPO Training Dataset=HelpSteer2025.1145.78
Instella-3B-SFT (TuluDPO)DPO Training Dataset=TuluDPO2025.1145.59
SFTBase Model=OLMo-2-7B-SFT, DPO Training Dataset=SFT2025.1145.04
Instella-3B-SFT (ORPO)DPO Training Dataset=ORPO2025.1144.88
Instella-3B-SFT (HelpSteer)DPO Training Dataset=HelpSteer2025.1143.94
Instella-3B-SFT (CodePref)DPO Training Dataset=CodePref2025.1143.72
Instella-3B-SFT (UltraFB)DPO Training Dataset=UltraFB2025.1143.69
Instella-3B-SFT (SFT)DPO Training Dataset=None (SFT Baseline)2025.1143.53