List your company

Visual Question Answering on HRBench 8K

76.25AccuracyFOCUS
32.98644.21855.4566.682Jun 26, 2025Aug 8, 2025Sep 20, 2025Nov 2, 2025Dec 15, 2025Jan 27, 2026Mar 11, 2026

Evaluation results

MethodLinks
FOCUSBase Model=Qwen-2.5-VL2025.0676.25
DeepEyes-7BThinking Level=Thinking with Images2026.0272.6
Thyme-7BThinking Level=Thinking with Images2026.0272.4
ViLAVT-7BThinking Level=Chatting with Images2026.0269.3
UG-SearchBase Model=LLaVA-OV-7B2025.1068.9
Qwen-2.5-VL2025.0668.62
Pixel-Reasoner-7BThinking Level=Thinking with Images2026.0266.9
ZoomEyeBase Model=LLaVA-OV-7B2025.1066.5
UG-SearchBase Model=Qwen2.5-VL-7B2025.1066.3
CropVLMReward=Accuracy, Backbone=Qwen 2.5 VL, Input Resolution=1792x1792, CropVLM Resolution=2048x20482025.1165.63
Qwen2.5-VL-7BThinking Level=Non-Thinking2026.0265.1
Qwen2.5-VL-7BThinking Level=Thinking about Images2026.0264.9
Qwen 2.5 VLInput Resolution=1792x17922025.1163.88
CropVLMBase Model=Qwen 2.5 VL 3B, Resolution=1024, Cropping Strategy=CropVLM2025.1163.63
CropVLMReward=LL, Backbone=Qwen 2.5 VL, Input Resolution=1792x1792, CropVLM Resolution=2048x20482025.1163.25
CropVLMBase Model=Qwen 2.5 VL 3B, Resolution=512, Cropping Strategy=CropVLM2025.1163
InternVL3-8BThinking Level=Non-Thinking2026.0262
Qwen 2.5 VL + CropVLMBase Model=Qwen 2.5 VL, Cropping Strategy=CropVLM, Input Resolution=2048x20482025.1160.75
CropVLMBase Model=Qwen 2.5 VL 3B, Resolution=2048, Cropping Strategy=CropVLM2025.1160.75
LLaVA-OneVision-7BThinking Level=Non-Thinking2026.0259.8
ThymeBase Model=Qwen2.5-VL-7B2025.1059
LLaVA-OV-7BBase Model=LLaVA-OV-7B2025.1058.4
VILASR-7BThinking Level=Thinking with Images2026.0256.3
Qwen2.5-VL-7BBase Model=Qwen2.5-VL-7B2025.1053.1
ViCropBase Model=Qwen2.5-VL-7B2025.1051.9
TextCoTBase Model=Qwen2.5-VL-7B2025.1050.6
SpaceR-7BThinking Level=Thinking about Images2026.0249.8
Qwen 2.5 VL + ViCrop (rel-att)Base Model=Qwen 2.5 VL, Cropping Strategy=ViCrop (rel-att), Input Resolution=448x4482025.1147.38
Qwen 2.5 VL + UV-CoTBase Model=Qwen 2.5 VL, Cropping Strategy=UV-CoT, Input Resolution=336x3362025.1147.25
Qwen 2.5 VL + ViCrop (grad-att)Base Model=Qwen 2.5 VL, Cropping Strategy=ViCrop (grad-att), Input Resolution=448x4482025.1146
MRoPEPositional Encoding Method=MRoPE, DIPE Enhancement=+DIPE2026.0345.13
Qwen 2.5 VLBase Model=Qwen 2.5 VL, Cropping Strategy=None, Input Resolution=448x4482025.1144.5
Qwen 2.5 VL 3BBase Model=Qwen 2.5 VL 3B, Resolution=-, Cropping Strategy=None2025.1144.5
Vanilla RoPEPositional Encoding Method=Vanilla RoPE, DIPE Enhancement=+DIPE2026.0344.12
MRoPE-IPositional Encoding Method=MRoPE-I, DIPE Enhancement=+DIPE2026.0343.88
MRoPE-IPositional Encoding Method=MRoPE-I, DIPE Enhancement=Base2026.0343.75
Vanilla RoPEPositional Encoding Method=Vanilla RoPE, DIPE Enhancement=Base2026.0342.63
MRoPEPositional Encoding Method=MRoPE, DIPE Enhancement=Base2026.0342.25
CropVLMBase Model=GPT 4.1 nano, Resolution=2048, Cropping Strategy=CropVLM2025.1140.5
LLaVA 1.5 + CropVLMBase Model=LLaVA 1.5, Cropping Strategy=CropVLM, Input Resolution=2048x20482025.1139.88
CropVLMBase Model=LLaVA 1.5 7B, Resolution=2048, Cropping Strategy=CropVLM2025.1139.88
CropVLMBase Model=GPT 4.1 nano, Resolution=1024, Cropping Strategy=CropVLM2025.1139.5
CropVLMBase Model=GPT 4.1 nano, Resolution=512, Cropping Strategy=CropVLM2025.1138.88
CropVLMBase Model=LLaVA 1.5 7B, Resolution=1024, Cropping Strategy=CropVLM2025.1138.38
LLaVA 1.5 + ViCrop (grad-att)Base Model=LLaVA 1.5, Cropping Strategy=ViCrop (grad-att), Input Resolution=336x3362025.1137.12
GPT 4.1 nanoBase Model=GPT 4.1 nano, Resolution=-, Cropping Strategy=None2025.1136.88
LLaVA 1.5 + ViCrop (rel-att)Base Model=LLaVA 1.5, Cropping Strategy=ViCrop (rel-att), Input Resolution=336x3362025.1136.5
LLaVA 1.5 + UV-CoTBase Model=LLaVA 1.5, Cropping Strategy=UV-CoT, Input Resolution=336x3362025.1135.88
CropVLMBase Model=LLaVA 1.5 7B, Resolution=512, Cropping Strategy=CropVLM2025.1135.88
LLaVA 1.5Base Model=LLaVA 1.5, Cropping Strategy=None, Input Resolution=336x3362025.1134.65
LLaVA 1.5 7BBase Model=LLaVA 1.5 7B, Resolution=-, Cropping Strategy=None2025.1134.65