List your company

Preference Aggregation on Preference Evaluation Suite Aggregate

36.68Average Preference Win RateAlphaToken
1.756810.823419.8928.9566Jun 1, 2026

Evaluation results

MethodLinks
AlphaTokenBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0636.68
SePOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0634.03
ConfPOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0633.82
TI-DPOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0632.33
DPOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0632.11
AlphaTokenBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0629.63
ConfPOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0626.68
SePOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0626.62
TI-DPOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0624.99
DPOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0620.94
AlphaTokenBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0617.62
SePOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0615.93
ConfPOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0615.07
BaseBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0614.12
TI-DPOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0613.9
DPOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0611.13
BaseBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.068.59
BaseBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.063.1