List your company

AlpacaEval 2.0 on UltraFeedback

30LCSSPO
2.5449.67216.823.928Oct 28, 2025

Evaluation results

MethodLinks
SSPOBackbone=Mistral (7B), Size=10%2025.103020.7
SSPOBackbone=Mistral (7B), Size=1%2025.1026.718.1
SSPOBackbone=Llama3 (8B), Size=10%2025.1020.720.8
SPABackbone=Mistral (7B), Size=10%2025.1019.118.7
KTOBackbone=Mistral (7B), Size=10%2025.1018.816.4
SPABackbone=Mistral (7B), Size=1%2025.1018.215.6
SimPOBackbone=Mistral (7B), Size=10%2025.1018.112.9
DPOBackbone=Mistral (7B), Size=10%2025.101813.6
DPOBackbone=Mistral (7B), Size=1%2025.101712.8
ORPOBackbone=Mistral (7B), Size=10%2025.1016.710.9
KTOBackbone=Llama3 (8B), Size=10%2025.1016.718.2
KTOBackbone=Mistral (7B), Size=1%2025.1016.414.9
SSRMBackbone=Mistral (7B), Size=10%2025.1016.213.3
SSRMBackbone=Llama3 (8B), Size=10%2025.1015.116.3
ORPOBackbone=Mistral (7B), Size=1%2025.101511.4
SSRMBackbone=Mistral (7B), Size=1%2025.1014.913.2
SSRMBackbone=Llama3 (8B), Size=1%2025.1014.912.8
SSPOBackbone=Llama3 (8B), Size=1%2025.1014.816
SPABackbone=Llama3 (8B), Size=10%2025.1014.516.6
KTOBackbone=Llama3 (8B), Size=1%2025.1014.415.8
SimPOBackbone=Llama3 (8B), Size=1%2025.1014.315.1
SPABackbone=Llama3 (8B), Size=1%2025.1013.415.3
SimPOBackbone=Mistral (7B), Size=1%2025.1013.28.3
DPOBackbone=Llama3 (8B), Size=10%2025.101313.7
SimPOBackbone=Llama3 (8B), Size=10%2025.101313.7
DPOBackbone=Llama3 (8B), Size=1%2025.1012.112.6
ORPOBackbone=Llama3 (8B), Size=10%2025.101010.9
ORPOBackbone=Llama3 (8B), Size=1%2025.109.410.3
SSPOBackbone=Phi-2 (2.7B), Size=10%2025.107.74.3
SSPOBackbone=Phi-2 (2.7B), Size=1%2025.107.24.1
SPABackbone=Phi-2 (2.7B), Size=10%2025.104.93.1
DPOBackbone=Phi-2 (2.7B), Size=10%2025.104.62.6
SSRMBackbone=Phi-2 (2.7B), Size=10%2025.104.42.6
KTOBackbone=Phi-2 (2.7B), Size=10%2025.104.42.6
SSRMBackbone=Phi-2 (2.7B), Size=1%2025.104.32
SimPOBackbone=Phi-2 (2.7B), Size=1%2025.1042.5
SimPOBackbone=Phi-2 (2.7B), Size=10%2025.1042.5
KTOBackbone=Phi-2 (2.7B), Size=1%2025.1042.5
SPABackbone=Phi-2 (2.7B), Size=1%2025.1042.6
ORPOBackbone=Phi-2 (2.7B), Size=10%2025.103.92.6
ORPOBackbone=Phi-2 (2.7B), Size=1%2025.103.72.3
DPOBackbone=Phi-2 (2.7B), Size=1%2025.103.62.5