List your company

Multiple Choice Questioning on RS-Neg MCQ (test)

65.73Object AccuracyNeFo
17.536430.048242.5655.0718Jun 18, 2026

Evaluation results

MethodLinks
NeFoBase Model=Qwen2.5-VL, Adaptation=Test-Time Learning2026.0665.7365.4962.365.46
NeFoBase Model=Qwen3-VL, Adaptation=Test-Time Learning2026.0664.963.8461.7864.55
SARBase Model=Qwen3-VL, Adaptation=Test-Time Learning2026.0661.6262.5859.9561.64
TentBase Model=Qwen3-VL, Adaptation=Test-Time Learning2026.0661.1161.8258.3861.02
TLMBase Model=Qwen3-VL, Adaptation=Test-Time Learning2026.0658.0958.6653.6657.87
Qwen3-VLBase Model=Qwen3-VL, Adaptation=None2026.0657.2958.1555.7657.3
TentBase Model=Qwen2.5-VL, Adaptation=Test-Time Learning2026.0656.1155.635255.77
SARBase Model=Qwen2.5-VL, Adaptation=Test-Time Learning2026.0655.8455.3752.0955.52
Qwen2.5-VLBase Model=Qwen2.5-VL, Adaptation=None2026.0654.2255.2553.1454.29
NeFoBase Model=GeoReason, Adaptation=Test-Time Learning2026.0652.7857.951.3153.39
TLMBase Model=Qwen2.5-VL, Adaptation=Test-Time Learning2026.0649.4248.4246.8649.43
SARBase Model=GeoReason, Adaptation=Test-Time Learning2026.0645.9153.651.0547.33
TLMBase Model=GeoReason, Adaptation=Test-Time Learning2026.0644.8549.5644.7645.5
GeoReasonBase Model=GeoReason, Adaptation=None2026.0644.3650.5749.7445.59
TentBase Model=GeoReason, Adaptation=Test-Time Learning2026.0634.1237.4232.7234.48
NeFoBase Model=RS-LLaVA, Adaptation=Test-Time Learning2026.0622.4132.4931.9424.46
RS-LLaVABase Model=RS-LLaVA, Adaptation=None2026.0621.5732.2431.4123.72
TLMBase Model=RS-LLaVA, Adaptation=Test-Time Learning2026.0620.6431.7330.6322.85
SARBase Model=RS-LLaVA, Adaptation=Test-Time Learning2026.0620.1931.2331.4122.48
TentBase Model=RS-LLaVA, Adaptation=Test-Time Learning2026.0619.3930.7230.3721.71