List your company

Visual Search and Perception-intensive Reasoning on Multi-benchmark Score Overall

64.59Overall ScoreStarve to Perceive
35.636443.153250.6758.1868May 18, 2026

Evaluation results

MethodLinks
Starve to PerceiveVisual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0564.59
Qwen2.5-VL + BA-SFT + VanillaRLVisual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0564.48
DeepEyesVisual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0561.77
ChainOfFocusVisual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0561.75
PixelReasonerVisual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0560.1
Qwen2.5-VL + BA-SFTVisual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0558.95
Qwen2.5-VLVisual Bandwidth Constraint (B)=No Constrain, Reported From=Other publications2026.0552.53
Starve to PerceiveVisual Bandwidth Constraint (B)=256, Tool-calling=True2026.0552.35
Qwen2.5-VL + BA-SFT + VanillaRLVisual Bandwidth Constraint (B)=256, Tool-calling=True2026.0551.54
Mini-o3Visual Bandwidth Constraint (B)=No Constrain, Tool-calling=True2026.0546.68
Qwen2.5-VL + BA-SFTVisual Bandwidth Constraint (B)=256, Tool-calling=True2026.0546.6
DeepEyesVisual Bandwidth Constraint (B)=256, Tool-calling=True2026.0545.57
ChainOfFocusVisual Bandwidth Constraint (B)=256, Tool-calling=True2026.0545.25
Mini-o3Visual Bandwidth Constraint (B)=256, Tool-calling=True2026.0536.75