List your company

Question Answering on TriviaQA (Metrics C, X, R+, R-)

79.9CBase
12.19629.77347.3564.927Feb 2, 2026

Evaluation results

MethodLinks
BaseBackbone=Llama-3.1-8B, Model Scale=Mid-Size (7-12B)2026.0279.914.853084.4———
BaseBackbone=Gemma-2-9B, Model Scale=Mid-Size (7-12B)2026.0277229077.8———
BaseBackbone=Gemma-3-12B, Model Scale=Mid-Size (7-12B)2026.0276.823.11076.9———
VeriFY-SMBackbone=Llama-3.1-8B, Model Scale=Mid-Size (7-12B)2026.0275.89.75309.288.793.591
VeriFY-MMBackbone=Llama-3.1-8B, Model Scale=Mid-Size (7-12B)2026.027510.16108.988.292.590.3
VeriFY-SMBackbone=Gemma-2-9B, Model Scale=Mid-Size (7-12B)2026.0274.71045010.888.294.391.2
VeriFY-MMBackbone=Gemma-2-9B, Model Scale=Mid-Size (7-12B)2026.0274.39.748011.288.493.991.1
SCBackbone=Gemma-2-9B, Model Scale=Mid-Size (7-12B)2026.027411.344010.286.794.390.4
VeriFY-NMBackbone=Llama-3.1-8B, Model Scale=Mid-Size (7-12B)2026.0273.810.46709.187.691.789.6
SCBackbone=Gemma-3-12B, Model Scale=Mid-Size (7-12B)2026.0272.813.74009.584.294.889.2
VeriFY-MMBackbone=Gemma-3-12B, Model Scale=Mid-Size (7-12B)2026.02728.864012.889.191.890.5
VeriFY-SMBackbone=Gemma-3-12B, Model Scale=Mid-Size (7-12B)2026.0270.97.277014.290.890.290.5
VeriFY-NMBackbone=Gemma-3-12B, Model Scale=Mid-Size (7-12B)2026.0270.810.165012.687.591.589.5
VeriFY-NMBackbone=Gemma-2-9B, Model Scale=Mid-Size (7-12B)2026.0270.56.680014.991.589.890.6
KPBackbone=Llama-3.1-8B, Model Scale=Mid-Size (7-12B)2026.0270.29.588011.588.188.988.5
BaseBackbone=Qwen2.5-7B, Model Scale=Mid-Size (7-12B)2026.0267.132.28067.6———
KPBackbone=Gemma-2-9B, Model Scale=Mid-Size (7-12B)2026.0264.36.91,34015.490.382.886.4
BaseBackbone=Llama-3.2-3B, Model Scale=Small-Size (2-4B)2026.0263.521.41,52074.8———
VeriFY-SMBackbone=Llama-3.2-3B, Model Scale=Small-Size (2-4B)2026.0262.412.763018.683.190.986.8
KPBackbone=Gemma-3-12B, Model Scale=Mid-Size (7-12B)2026.0262.46.41,45016.890.781.285.7
VeriFY-MMBackbone=Llama-3.2-3B, Model Scale=Small-Size (2-4B)2026.0262.312.463018.983.490.886.9
VeriFY-SMBackbone=Qwen2.5-7B, Model Scale=Mid-Size (7-12B)2026.0261.110.57302185.389.387.3
VeriFY-MMBackbone=Qwen2.5-7B, Model Scale=Mid-Size (7-12B)2026.0260.99.876021.786.188.987.5
VeriFY-NMBackbone=Llama-3.2-3B, Model Scale=Small-Size (2-4B)2026.0260.514.961018.580.290.885.2
VeriFY-NMBackbone=Qwen2.5-7B, Model Scale=Mid-Size (7-12B)2026.0259.38.98802386.987.187
BaseBackbone=Gemma-2-2B, Model Scale=Small-Size (2-4B)2026.0258.540.87058.9———
SCBackbone=Llama-3.1-8B, Model Scale=Mid-Size (7-12B)2026.0258.42.12,1501896.673.183.2
BaseBackbone=Gemma-3-4B, Model Scale=Small-Size (2-4B)2026.0257.142.81057.1———
VeriFY-SMBackbone=Gemma-2-2B, Model Scale=Small-Size (2-4B)2026.0255.519.653019.673.991.281.7
BaseBackbone=Qwen2.5-3B, Model Scale=Small-Size (2-4B)2026.0255.540.540057.8———
SCBackbone=Qwen2.5-7B, Model Scale=Mid-Size (7-12B)2026.0254.96.91,2102688.881.985.2
VeriFY-MMBackbone=Gemma-2-2B, Model Scale=Small-Size (2-4B)2026.0254.417.562021.975.689.782
KPBackbone=Llama-3.2-3B, Model Scale=Small-Size (2-4B)2026.0254.311.41,01024.282.784.383.5
KPBackbone=Qwen2.5-7B, Model Scale=Mid-Size (7-12B)2026.0252.97.91,410258778.982.8
SCBackbone=Gemma-3-4B, Model Scale=Small-Size (2-4B)2026.0252.722.544020.570.192.379.7
VeriFY-MMBackbone=Gemma-3-4B, Model Scale=Small-Size (2-4B)2026.0252.514.18302578.886.382.4
VeriFY-SMBackbone=Qwen2.5-3B, Model Scale=Small-Size (2-4B)2026.0252.219.158022.973.29080.7
VeriFY-SMBackbone=Gemma-3-4B, Model Scale=Small-Size (2-4B)2026.0251.710.492028.783.28584.1
SCBackbone=Gemma-2-2B, Model Scale=Small-Size (2-4B)2026.025016.486024.975.285.380
VeriFY-MMBackbone=Qwen2.5-3B, Model Scale=Small-Size (2-4B)2026.025013.78302878.585.782
VeriFY-NMBackbone=Gemma-2-2B, Model Scale=Small-Size (2-4B)2026.0249.313.21,01027.478.982.980.9
KPBackbone=Gemma-2-2B, Model Scale=Small-Size (2-4B)2026.0246.613.21,25027.87878.978.5
VeriFY-NMBackbone=Qwen2.5-3B, Model Scale=Small-Size (2-4B)2026.0246.6111,0403280.981.781.3
VeriFY-NMBackbone=Gemma-3-4B, Model Scale=Small-Size (2-4B)2026.0244.16.71,45034.786.875.280.6
KPBackbone=Gemma-3-4B, Model Scale=Small-Size (2-4B)2026.0241.18.11,64034.483.571.677.1
KPBackbone=Qwen2.5-3B, Model Scale=Small-Size (2-4B)2026.0233.55.72,23038.585.56070.5
SCBackbone=Llama-3.2-3B, Model Scale=Small-Size (2-4B)2026.0232.11.73,14034.99550.566
SCBackbone=Qwen2.5-3B, Model Scale=Small-Size (2-4B)2026.0214.81.74,06042.889.626.841.2