List your company

Relevance Prediction on In-the-Wild W-Eval

52.77Class 1 MetricTaoSR-AGRL
44.158846.394448.6350.8656Oct 9, 2025

Evaluation results

MethodLinks
TaoSR-AGRLBackbone=TbStar-DPO2025.1052.7764.3446.2282.7986.661.5374.28
GRPO-PRBackbone=TbStar-DPO2025.1045.4963.5645.0882.7686.5959.2273.95
GRPOBackbone=TbStar-DPO2025.1045.4162.9545.9382.7286.4959.2573.83
TbStar-DPOBackbone=TbStar (42B MoE)2025.1044.4963.2645.9582.5986.3859.0773.7