List your company

General Language Capability Evaluation on General Capability Suite Aggregate

62.51General Capability Avg. AccuracyBase
37.633244.091650.5557.0084Jun 1, 2026

Evaluation results

MethodLinks
BaseBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0662.51
AlphaTokenBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0662.29
TI-DPOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0661.61
ConfPOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0661.49
DPOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0660.8
SePOBackbone=Qwen-3.5-9B, Warm-start Reference=UltraChat-200k2026.0660.21
BaseBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0645.14
AlphaTokenBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0644.42
ConfPOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0644.3
TI-DPOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0644.28
DPOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0643.55
SePOBackbone=Gemma-3-4B, Warm-start Reference=UltraChat-200k2026.0642.69
BaseBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0641.91
AlphaTokenBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0641.37
TI-DPOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0640.93
ConfPOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0640.46
DPOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0640.18
SePOBackbone=Llama-3.2-3B, Warm-start Reference=UltraChat-200k2026.0638.59