condition,qtype,pair,quality,lo,hi,n,abstained A1,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 A1,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.0 A1,multi_hop,Llama-3.2-3B,1.0,1.0,1.0,40,0.0 A1,multi_hop,Qwen2.5-3B,1.0,1.0,1.0,40,0.0 A1,negation,Llama-3.2-3B,0.9,0.825,0.9625,80,0.0 A1,negation,Qwen2.5-3B,0.9625,0.9125,1.0,80,0.0 A1,revision,Llama-3.2-3B,0.75,0.6625,0.8375,80,0.0 A1,revision,Qwen2.5-3B,0.875,0.8125,0.9375,80,0.0 A1,temporal,Llama-3.2-3B,0.625,0.475,0.775,40,0.0 A1,temporal,Qwen2.5-3B,0.55,0.4,0.7,40,0.0 A1,unanswerable,Llama-3.2-3B,0.95,0.9,0.9875,80,0.95 A1,unanswerable,Qwen2.5-3B,0.975,0.9375,1.0,80,0.975 A1,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 A1,unit_conversion,Qwen2.5-3B,0.575,0.41187500000000027,0.725,40,0.0 A3|budget_tokens=512|blind,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 A3|budget_tokens=512|blind,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.0 A3|budget_tokens=512|blind,multi_hop,Llama-3.2-3B,0.0,0.0,0.0,40,1.0 A3|budget_tokens=512|blind,multi_hop,Qwen2.5-3B,0.0,0.0,0.0,40,1.0 A3|budget_tokens=512|blind,negation,Llama-3.2-3B,0.8625,0.7875,0.925,80,0.0 A3|budget_tokens=512|blind,negation,Qwen2.5-3B,0.9,0.8309375000000001,0.95,80,0.0 A3|budget_tokens=512|blind,revision,Llama-3.2-3B,0.8375,0.7625,0.9125,80,0.0 A3|budget_tokens=512|blind,revision,Qwen2.5-3B,0.7,0.6059375000000001,0.7875,80,0.0125 A3|budget_tokens=512|blind,temporal,Llama-3.2-3B,0.65,0.5,0.8,40,0.0 A3|budget_tokens=512|blind,temporal,Qwen2.5-3B,0.6,0.45,0.75,40,0.0 A3|budget_tokens=512|blind,unanswerable,Llama-3.2-3B,1.0,1.0,1.0,80,1.0 A3|budget_tokens=512|blind,unanswerable,Qwen2.5-3B,1.0,1.0,1.0,80,1.0 A3|budget_tokens=512|blind,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.925 A3|budget_tokens=512|blind,unit_conversion,Qwen2.5-3B,0.0,0.0,0.0,40,0.675 A4|budget_tokens=512|blind,aggregation,Llama-3.2-3B,0.025,0.0,0.075,40,0.0 A4|budget_tokens=512|blind,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.35 A4|budget_tokens=512|blind,multi_hop,Llama-3.2-3B,0.3,0.15,0.45,40,0.65 A4|budget_tokens=512|blind,multi_hop,Qwen2.5-3B,0.475,0.325,0.625,40,0.475 A4|budget_tokens=512|blind,negation,Llama-3.2-3B,0.95,0.8875,1.0,80,0.0125 A4|budget_tokens=512|blind,negation,Qwen2.5-3B,0.725,0.625,0.8125,80,0.175 A4|budget_tokens=512|blind,revision,Llama-3.2-3B,0.125,0.0625,0.2125,80,0.375 A4|budget_tokens=512|blind,revision,Qwen2.5-3B,0.2,0.1125,0.3,80,0.6125 A4|budget_tokens=512|blind,temporal,Llama-3.2-3B,0.325,0.175,0.475,40,0.325 A4|budget_tokens=512|blind,temporal,Qwen2.5-3B,0.475,0.325,0.625,40,0.15 A4|budget_tokens=512|blind,unanswerable,Llama-3.2-3B,1.0,1.0,1.0,80,1.0 A4|budget_tokens=512|blind,unanswerable,Qwen2.5-3B,1.0,1.0,1.0,80,1.0 A4|budget_tokens=512|blind,unit_conversion,Llama-3.2-3B,0.025,0.0,0.075,40,0.575 A4|budget_tokens=512|blind,unit_conversion,Qwen2.5-3B,0.325,0.175,0.475,40,0.6 A5|budget_tokens=512|blind,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.475 A5|budget_tokens=512|blind,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.325 A5|budget_tokens=512|blind,multi_hop,Llama-3.2-3B,0.1,0.025,0.2,40,0.9 A5|budget_tokens=512|blind,multi_hop,Qwen2.5-3B,0.15,0.05,0.275,40,0.75 A5|budget_tokens=512|blind,negation,Llama-3.2-3B,0.5,0.375,0.6,80,0.375 A5|budget_tokens=512|blind,negation,Qwen2.5-3B,0.4875,0.36843750000000014,0.6,80,0.475 A5|budget_tokens=512|blind,revision,Llama-3.2-3B,0.075,0.025,0.15,80,0.8375 A5|budget_tokens=512|blind,revision,Qwen2.5-3B,0.0375,0.0,0.1,80,0.85 A5|budget_tokens=512|blind,temporal,Llama-3.2-3B,0.1,0.025,0.2,40,0.85 A5|budget_tokens=512|blind,temporal,Qwen2.5-3B,0.075,0.0,0.175,40,0.8 A5|budget_tokens=512|blind,unanswerable,Llama-3.2-3B,1.0,1.0,1.0,80,1.0 A5|budget_tokens=512|blind,unanswerable,Qwen2.5-3B,1.0,1.0,1.0,80,1.0 A5|budget_tokens=512|blind,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.75 A5|budget_tokens=512|blind,unit_conversion,Qwen2.5-3B,0.15,0.05,0.275,40,0.45 B2|bits=8,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 B2|bits=8,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.0 B2|bits=8,multi_hop,Llama-3.2-3B,1.0,1.0,1.0,40,0.0 B2|bits=8,multi_hop,Qwen2.5-3B,1.0,1.0,1.0,40,0.0 B2|bits=8,negation,Llama-3.2-3B,0.9,0.825,0.9625,80,0.0 B2|bits=8,negation,Qwen2.5-3B,0.9375,0.8809375000000002,0.9875,80,0.0 B2|bits=8,revision,Llama-3.2-3B,0.7625,0.675,0.85,80,0.0 B2|bits=8,revision,Qwen2.5-3B,0.875,0.8125,0.9375,80,0.0 B2|bits=8,temporal,Llama-3.2-3B,0.625,0.475,0.775,40,0.0 B2|bits=8,temporal,Qwen2.5-3B,0.55,0.4,0.7,40,0.0 B2|bits=8,unanswerable,Llama-3.2-3B,0.95,0.9,0.9875,80,0.95 B2|bits=8,unanswerable,Qwen2.5-3B,0.975,0.9375,1.0,80,0.975 B2|bits=8,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 B2|bits=8,unit_conversion,Qwen2.5-3B,0.6,0.45,0.75,40,0.0 B3|keep_frac=0.25,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 B3|keep_frac=0.25,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.0 B3|keep_frac=0.25,multi_hop,Llama-3.2-3B,0.15,0.05,0.275,40,0.275 B3|keep_frac=0.25,multi_hop,Qwen2.5-3B,0.175,0.075,0.3,40,0.1 B3|keep_frac=0.25,negation,Llama-3.2-3B,0.725,0.65,0.8,80,0.0 B3|keep_frac=0.25,negation,Qwen2.5-3B,0.9125,0.85,0.975,80,0.0 B3|keep_frac=0.25,revision,Llama-3.2-3B,0.15,0.06843750000000012,0.2375,80,0.4875 B3|keep_frac=0.25,revision,Qwen2.5-3B,0.1,0.025,0.1875,80,0.0 B3|keep_frac=0.25,temporal,Llama-3.2-3B,0.575,0.425,0.725,40,0.0 B3|keep_frac=0.25,temporal,Qwen2.5-3B,0.55,0.41187500000000027,0.7,40,0.0 B3|keep_frac=0.25,unanswerable,Llama-3.2-3B,0.9375,0.875,0.9875,80,0.9375 B3|keep_frac=0.25,unanswerable,Qwen2.5-3B,0.9875,0.9625,1.0,80,0.9875 B3|keep_frac=0.25,unit_conversion,Llama-3.2-3B,0.025,0.0,0.075,40,0.65 B3|keep_frac=0.25,unit_conversion,Qwen2.5-3B,0.075,0.0,0.15,40,0.0 B5|keep_frac=0.25|aware,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 B5|keep_frac=0.25|aware,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.0 B5|keep_frac=0.25|aware,multi_hop,Llama-3.2-3B,0.95,0.875,1.0,40,0.0 B5|keep_frac=0.25|aware,multi_hop,Qwen2.5-3B,0.575,0.425,0.725,40,0.0 B5|keep_frac=0.25|aware,negation,Llama-3.2-3B,0.85,0.7625,0.925,80,0.0 B5|keep_frac=0.25|aware,negation,Qwen2.5-3B,0.9625,0.925,1.0,80,0.0 B5|keep_frac=0.25|aware,revision,Llama-3.2-3B,0.7625,0.6875,0.8375,80,0.0 B5|keep_frac=0.25|aware,revision,Qwen2.5-3B,0.275,0.175,0.375,80,0.0 B5|keep_frac=0.25|aware,temporal,Llama-3.2-3B,0.7,0.55,0.85,40,0.0 B5|keep_frac=0.25|aware,temporal,Qwen2.5-3B,0.55,0.4,0.7131249999999993,40,0.0 B5|keep_frac=0.25|aware,unanswerable,Llama-3.2-3B,0.95,0.9,0.9875,80,0.95 B5|keep_frac=0.25|aware,unanswerable,Qwen2.5-3B,0.975,0.9375,1.0,80,0.975 B5|keep_frac=0.25|aware,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.0 B5|keep_frac=0.25|aware,unit_conversion,Qwen2.5-3B,0.6,0.425,0.725,40,0.0