List your company

Factuality-based Question Answering on FreshQA 2025/11/24

44CBase
7.617.0526.535.95Feb 2, 2026

Evaluation results

MethodLinks
BaseBackbone=Gemma-2-9b, Size Class=Mid-Size Models (7B-12B)2026.024444128850———
BaseBackbone=Gemma-3-12b, Size Class=Mid-Size Models (7B-12B)2026.024456——44———
VeriFY-MMBackbone=Gemma-2-9b, Size Class=Mid-Size Models (7B-12B)2026.0238.427.65.428.66658.287.769.9
BaseBackbone=Llama-3.1-8B, Size Class=Mid-Size Models (7B-12B)2026.0237.444.817.882.245.5———
VeriFY-NMBackbone=Gemma-3-12b, Size Class=Mid-Size Models (7B-12B)2026.0236.427729.663.457.483.968.2
VeriFY-SMBackbone=Gemma-2-9b, Size Class=Mid-Size Models (7B-12B)2026.023627.86.829.463.856.484.167.5
BaseBackbone=Llama-3.2-3B, Size Class=Small-Size Models (2B-4B)2026.0235.847.2178343.1———
VeriFY-NMBackbone=Llama-3.1-8B, Size Class=Mid-Size Models (7B-12B)2026.0235.638.64.421.474.2488962.4
VeriFY-MMBackbone=Gemma-3-12b, Size Class=Mid-Size Models (7B-12B)2026.0235.629.6727.865.254.683.666
VeriFY-NMBackbone=Gemma-2-9b, Size Class=Mid-Size Models (7B-12B)2026.0235.2247.633.259.259.582.269
VeriFY-SMBackbone=Gemma-3-12b, Size Class=Mid-Size Models (7B-12B)2026.0235.224.67.632.659.858.982.268.6
VeriFY-MMBackbone=Llama-3.1-8B, Size Class=Mid-Size Models (7B-12B)2026.023536.25.223.671.249.287.162.8
BaseBackbone=Gemma-2-2b, Size Class=Small-Size Models (2B-4B)2026.0234.658.27.292.837.3———
VeriFY-SMBackbone=Llama-3.1-8B, Size Class=Mid-Size Models (7B-12B)2026.0234.238.63.823.472.8479061.7
BaseBackbone=Gemma-3-4b, Size Class=Small-Size Models (2B-4B)2026.0233.466.6——33.4———
BaseBackbone=Qwen2.5-7B, Size Class=Mid-Size Models (7B-12B)2026.0232.261.66.293.834.3———
VeriFY-NMBackbone=Llama-3.2-3B, Size Class=Small-Size Models (2B-4B)2026.0231.435.86.226.667.246.783.559.9
VeriFY-MMBackbone=Gemma-2-2b, Size Class=Small-Size Models (2B-4B)2026.0228.829.66.435.258.449.381.861.5
VeriFY-SMBackbone=Llama-3.2-3B, Size Class=Small-Size Models (2B-4B)2026.0228.633.46.831.26246.180.858.7
VeriFY-MMBackbone=Llama-3.2-3B, Size Class=Small-Size Models (2B-4B)2026.0228.433.68.229.86245.877.657.6
VeriFY-SMBackbone=Gemma-2-2b, Size Class=Small-Size Models (2B-4B)2026.0228347.630.46245.278.757.4
BaseBackbone=Qwen2.5-3B, Size Class=Small-Size Models (2B-4B)2026.022854.617.482.633.9———
KPBackbone=Gemma-3-12b, Size Class=Mid-Size Models (7B-12B)2026.0226.41517.241.441.463.860.562.1
KPBackbone=Gemma-2-9b, Size Class=Mid-Size Models (7B-12B)2026.0226.212.816.644.43967.261.264.1
KPBackbone=Llama-3.1-8B, Size Class=Mid-Size Models (7B-12B)2026.0225.820.812.44146.655.467.560.9
VeriFY-MMBackbone=Gemma-3-4b, Size Class=Small-Size Models (2B-4B)2026.0225.6277.44052.648.777.659.8
VeriFY-SMBackbone=Gemma-3-4b, Size Class=Small-Size Models (2B-4B)2026.0225.419.8945.845.256.273.863.8
VeriFY-MMBackbone=Qwen2.5-7B, Size Class=Mid-Size Models (7B-12B)2026.0224.423.68.443.64850.874.460.4
VeriFY-SMBackbone=Qwen2.5-7B, Size Class=Mid-Size Models (7B-12B)2026.0224.424.49.24248.85072.659.2
KPBackbone=Gemma-2-2b, Size Class=Small-Size Models (2B-4B)2026.0223.62010.44643.654.169.460.8
VeriFY-NMBackbone=Gemma-2-2b, Size Class=Small-Size Models (2B-4B)2026.0223.627.610.83851.246.168.655.1
VeriFY-NMBackbone=Gemma-3-4b, Size Class=Small-Size Models (2B-4B)2026.0223.218.810484255.269.961.7
VeriFY-NMBackbone=Qwen2.5-7B, Size Class=Mid-Size Models (7B-12B)2026.022323.29.444.446.249.87158.5
KPBackbone=Llama-3.2-3B, Size Class=Small-Size Models (2B-4B)2026.0221.621.412.444.64350.263.556.1
VeriFY-SMBackbone=Qwen2.5-3B, Size Class=Small-Size Models (2B-4B)2026.0219.829.67.64349.440.172.351.6
KPBackbone=Gemma-3-4b, Size Class=Small-Size Models (2B-4B)2026.0219.414.81451.834.256.758.157.4
VeriFY-MMBackbone=Qwen2.5-3B, Size Class=Small-Size Models (2B-4B)2026.0218.821.69.450.240.446.566.754.8
VeriFY-NMBackbone=Qwen2.5-3B, Size Class=Small-Size Models (2B-4B)2026.0217.819.811.45137.647.36153.3
KPBackbone=Qwen2.5-7B, Size Class=Mid-Size Models (7B-12B)2026.0217.413.414.454.830.856.554.755.6
KPBackbone=Qwen2.5-3B, Size Class=Small-Size Models (2B-4B)2026.029818651752.933.340.9