List your company

Human Preference Evaluation on EQ-Bench Creative and LongBench Write (60 pairs)

67.5WinratePOLARIS
50.54854.94959.3563.751Jun 2, 2026

Evaluation results

MethodLinks
POLARISComparison Baseline=Qwen3.5-9B2026.0667.557.52022.5
POLARISComparison Baseline=Qwen3.5-27B2026.0651.23532.532.5