List your company

Language Model Alignment Evaluation on Arena-Hard v0.1

35.2Win Rate (%)HyPO
4.20812.25420.328.346Feb 12, 2026

Evaluation results

MethodLinks
HyPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0235.2
HyPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0233.5
TR-DPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0232.5
SimPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0232.1
DPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0231.5
RainbowPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0231.3
TR-DPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0231
KTOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0230.5
FocalPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0230.2
SimPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0230.1
CPOModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0230
RainbowPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0228.6
FocalPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0227.9
HyPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0225.2
SLiC-HFModel Family=Llama-3, Model State=Instruct, Model Parameters (B)=8B2026.0225.1
DPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0223
CPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0221
SimPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0220.5
FocalPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0218.7
KTOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0218.4
TR-DPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0218.2
RainbowPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0218.2
KTOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0217.5
SLiC-HFModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0216.9
DPOModel Family=Mistral, Model State=Instruct, Model Parameters (B)=7B2026.0215.4
SLiC-HFModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0214.3
HyPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.0213.9
CPOModel Family=Llama-3, Model State=Base, Model Parameters (B)=8B2026.0212.2
SimPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.0211.2
TR-DPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.029.5
RainbowPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.029.2
FocalPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.028.2
DPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.027.9
KTOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.026.6
CPOModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.026.4
SLiC-HFModel Family=Mistral, Model State=Base, Model Parameters (B)=7B2026.025.4