List your company

AlpacaEval 2.0 on DSP Business

17.9LCSSPO
2.0926.19610.314.404Oct 28, 2025

Evaluation results

MethodLinks
SSPOBackbone=Mistral (7B), Size=10%2025.1017.98.8
SSPOBackbone=Mistral (7B), Size=1%2025.1017.27.1
KTOBackbone=Mistral (7B), Size=10%2025.1016.77.5
DPOBackbone=Mistral (7B), Size=10%2025.10166.8
ORPOBackbone=Mistral (7B), Size=10%2025.10167
SPABackbone=Mistral (7B), Size=10%2025.10167.2
ORPOBackbone=Mistral (7B), Size=1%2025.1015.96.5
SimPOBackbone=Mistral (7B), Size=10%2025.1015.97.1
SSRMBackbone=Mistral (7B), Size=10%2025.1015.96.9
KTOBackbone=Mistral (7B), Size=1%2025.1015.76.8
SimPOBackbone=Mistral (7B), Size=1%2025.1015.56.5
SPABackbone=Mistral (7B), Size=1%2025.1015.46.5
SSRMBackbone=Mistral (7B), Size=1%2025.1015.26.7
DPOBackbone=Mistral (7B), Size=1%2025.10156.5
SSPOBackbone=Llama3 (8B), Size=10%2025.105.75.7
ORPOBackbone=Llama3 (8B), Size=10%2025.104.64.7
KTOBackbone=Llama3 (8B), Size=10%2025.104.44.6
SPABackbone=Llama3 (8B), Size=10%2025.104.34.1
SSRMBackbone=Llama3 (8B), Size=10%2025.103.83.5
DPOBackbone=Llama3 (8B), Size=10%2025.103.73.6
SSPOBackbone=Llama3 (8B), Size=1%2025.103.73.6
ORPOBackbone=Llama3 (8B), Size=1%2025.103.63.1
SimPOBackbone=Llama3 (8B), Size=10%2025.103.63.5
KTOBackbone=Llama3 (8B), Size=1%2025.103.23.1
SSRMBackbone=Llama3 (8B), Size=1%2025.103.12.9
SPABackbone=Llama3 (8B), Size=1%2025.1032.7
DPOBackbone=Llama3 (8B), Size=1%2025.102.72.1
SimPOBackbone=Llama3 (8B), Size=1%2025.102.72.1