List your company

MT-Bench Evaluation on UltraFeedback

8.1MT-Bench ScoreSPA
5.2926.0216.757.479Oct 28, 2025

Evaluation results

MethodLinks
SPABackbone=Llama3 (8B), Size=10%2025.108.1
DPOBackbone=Llama3 (8B), Size=1%2025.108
DPOBackbone=Llama3 (8B), Size=10%2025.108
ORPOBackbone=Llama3 (8B), Size=1%2025.108
SimPOBackbone=Llama3 (8B), Size=1%2025.108
KTOBackbone=Llama3 (8B), Size=10%2025.108
SSPOBackbone=Llama3 (8B), Size=1%2025.108
ORPOBackbone=Llama3 (8B), Size=10%2025.107.9
SimPOBackbone=Llama3 (8B), Size=10%2025.107.9
KTOBackbone=Llama3 (8B), Size=1%2025.107.9
SPABackbone=Llama3 (8B), Size=1%2025.107.9
SSPOBackbone=Llama3 (8B), Size=10%2025.107.9
SPABackbone=Mistral (7B), Size=10%2025.107.8
SPABackbone=Mistral (7B), Size=1%2025.107.7
SSPOBackbone=Mistral (7B), Size=1%2025.107.7
SSPOBackbone=Mistral (7B), Size=10%2025.107.7
DPOBackbone=Mistral (7B), Size=1%2025.107.6
DPOBackbone=Mistral (7B), Size=10%2025.107.6
SimPOBackbone=Mistral (7B), Size=1%2025.107.6
KTOBackbone=Mistral (7B), Size=1%2025.107.6
KTOBackbone=Mistral (7B), Size=10%2025.107.6
ORPOBackbone=Mistral (7B), Size=1%2025.107.5
ORPOBackbone=Mistral (7B), Size=10%2025.107.5
SimPOBackbone=Mistral (7B), Size=10%2025.107.5
DPOBackbone=Phi-2 (2.7B), Size=1%2025.106.3
DPOBackbone=Phi-2 (2.7B), Size=10%2025.106.3
ORPOBackbone=Phi-2 (2.7B), Size=1%2025.106.3
ORPOBackbone=Phi-2 (2.7B), Size=10%2025.106.3
SimPOBackbone=Phi-2 (2.7B), Size=1%2025.106.3
SimPOBackbone=Phi-2 (2.7B), Size=10%2025.106.3
SSRMBackbone=Phi-2 (2.7B), Size=10%2025.106.3
KTOBackbone=Phi-2 (2.7B), Size=1%2025.106.3
KTOBackbone=Phi-2 (2.7B), Size=10%2025.106.3
SPABackbone=Phi-2 (2.7B), Size=1%2025.106.3
SPABackbone=Phi-2 (2.7B), Size=10%2025.106.3
SSPOBackbone=Phi-2 (2.7B), Size=1%2025.106.3
SSPOBackbone=Phi-2 (2.7B), Size=10%2025.106.3
SSRMBackbone=Phi-2 (2.7B), Size=1%2025.106.2
SSRMBackbone=Llama3 (8B), Size=1%2025.106.2
SSRMBackbone=Llama3 (8B), Size=10%2025.106.2
SSRMBackbone=Mistral (7B), Size=10%2025.105.5
SSRMBackbone=Mistral (7B), Size=1%2025.105.4