List your company

Task#1 on STAR

99.88AccuracyQwen3-VL-8B S2(KGRPO)
2.3827.692553.00578.3175Oct 22, 2025

Evaluation results

MethodLinks
Qwen3-VL-8B S2(KGRPO)Backbone=Qwen3-VL-8B, Setting=S2(KGRPO)2025.1099.8896.4
Qwen3-VL-4B S2(KGRPO)Backbone=Qwen3-VL-4B, Setting=S2(KGRPO)2025.1099.7595.36
Qwen3-VL-2B S2(KGRPO)Backbone=Qwen3-VL-2B, Setting=S2(KGRPO)2025.1099.3894.49
LLaVA-NEXT-34B S2(SimPO)Backbone=LLaVA-NEXT-34B, Setting=S2(SimPO)2025.1098.2592.96
GPT-4oBackbone=GPT-4o2025.1094.25—
KGRPOBackbone=Qwen2.5-VL-7B, Settings=S2(KGRPO)2025.1079.8886.4
Qwen2.5-VL-7B S2(KGRPO)Backbone=Qwen2.5-VL-7B, Setting=S2(KGRPO)2025.1079.8886.4
S1(Single)Backbone=Qwen2.5-VL-7B, Settings=S1(Single)2025.1077.1382.47
Qwen2.5-VL-32B S2(SimPO)Backbone=Qwen2.5-VL-32B, Setting=S2(SimPO)2025.1076.3782.01
GRPOBackbone=Qwen2.5-VL-7B, Settings=S2(GRPO)2025.1075.2583.07
KGRPOBackbone=Qwen2.5-VL-3B, Settings=S2(KGRPO)2025.107581.49
Qwen2.5-VL-3B S2(KGRPO)Backbone=Qwen2.5-VL-3B, Setting=S2(KGRPO)2025.107581.49
SimPOBackbone=Qwen2.5-VL-3B, Settings=S2(SimPO)2025.107179.03
SimPOBackbone=Qwen2.5-VL-7B, Settings=S2(SimPO)2025.1069.6382.96
GPT-4o-miniBackbone=GPT-4o-mini, Settings=Zero-shot2025.1067.5—
GPT-4o-miniBackbone=GPT-4o-mini2025.1067.5—
LLaVA-1.5/NEXT-7B S2(SimPO)Backbone=LLaVA-1.5/NEXT-7B, Setting=S2(SimPO)2025.1067.3848.86
DPOBackbone=Qwen2.5-VL-7B, Settings=S2(DPO)2025.1066.582.11
ORPOBackbone=Qwen2.5-VL-7B, Settings=S2(ORPO)2025.1065.7581.96
S1(Full)Backbone=Qwen2.5-VL-7B, Settings=S1(Full)2025.1064.8881.79
GRPOBackbone=Qwen2.5-VL-3B, Settings=S2(GRPO)2025.106076.49
DPOBackbone=Qwen2.5-VL-3B, Settings=S2(DPO)2025.1055.573.28
S1(Single)Backbone=Qwen2.5-VL-3B, Settings=S1(Single)2025.105162.07
GPT-4oBackbone=GPT-4o, Settings=Zero-shot2025.1043.75—
Qwen3-VL-30BBackbone=Qwen3-VL-30B2025.1043.75—
S1(Full)Backbone=Qwen2.5-VL-3B, Settings=S1(Full)2025.1042.7552.67
ORPOBackbone=Qwen2.5-VL-3B, Settings=S2(ORPO)2025.103964.79
Qwen2.5VL-72BBackbone=Qwen2.5VL-72B2025.1038.25—
GPT-4vBackbone=GPT-4v, Settings=Zero-shot2025.1037.75—
GPT-4vBackbone=GPT-4v2025.1037.75—
QVQ-72BBackbone=QVQ-72B2025.1030.75—
Zero-shotBackbone=Qwen2.5-VL-3B, Settings=Zero-shot2025.1018.25—
Zero-shotBackbone=Qwen2.5-VL-7B, Settings=Zero-shot2025.106.13—