SPB Git

spb/wp30_uqo

Public
6.4 KB · 100 lines csv
1condition,qtype,pair,quality,lo,hi,n,abstained2A1,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.03A1,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.04A1,multi_hop,Llama-3.2-3B,1.0,1.0,1.0,40,0.05A1,multi_hop,Qwen2.5-3B,1.0,1.0,1.0,40,0.06A1,negation,Llama-3.2-3B,0.9,0.825,0.9625,80,0.07A1,negation,Qwen2.5-3B,0.9625,0.9125,1.0,80,0.08A1,revision,Llama-3.2-3B,0.75,0.6625,0.8375,80,0.09A1,revision,Qwen2.5-3B,0.875,0.8125,0.9375,80,0.010A1,temporal,Llama-3.2-3B,0.625,0.475,0.775,40,0.011A1,temporal,Qwen2.5-3B,0.55,0.4,0.7,40,0.012A1,unanswerable,Llama-3.2-3B,0.95,0.9,0.9875,80,0.9513A1,unanswerable,Qwen2.5-3B,0.975,0.9375,1.0,80,0.97514A1,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.015A1,unit_conversion,Qwen2.5-3B,0.575,0.41187500000000027,0.725,40,0.016A3|budget_tokens=512|blind,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.017A3|budget_tokens=512|blind,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.018A3|budget_tokens=512|blind,multi_hop,Llama-3.2-3B,0.0,0.0,0.0,40,1.019A3|budget_tokens=512|blind,multi_hop,Qwen2.5-3B,0.0,0.0,0.0,40,1.020A3|budget_tokens=512|blind,negation,Llama-3.2-3B,0.8625,0.7875,0.925,80,0.021A3|budget_tokens=512|blind,negation,Qwen2.5-3B,0.9,0.8309375000000001,0.95,80,0.022A3|budget_tokens=512|blind,revision,Llama-3.2-3B,0.8375,0.7625,0.9125,80,0.023A3|budget_tokens=512|blind,revision,Qwen2.5-3B,0.7,0.6059375000000001,0.7875,80,0.012524A3|budget_tokens=512|blind,temporal,Llama-3.2-3B,0.65,0.5,0.8,40,0.025A3|budget_tokens=512|blind,temporal,Qwen2.5-3B,0.6,0.45,0.75,40,0.026A3|budget_tokens=512|blind,unanswerable,Llama-3.2-3B,1.0,1.0,1.0,80,1.027A3|budget_tokens=512|blind,unanswerable,Qwen2.5-3B,1.0,1.0,1.0,80,1.028A3|budget_tokens=512|blind,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.92529A3|budget_tokens=512|blind,unit_conversion,Qwen2.5-3B,0.0,0.0,0.0,40,0.67530A4|budget_tokens=512|blind,aggregation,Llama-3.2-3B,0.025,0.0,0.075,40,0.031A4|budget_tokens=512|blind,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.3532A4|budget_tokens=512|blind,multi_hop,Llama-3.2-3B,0.3,0.15,0.45,40,0.6533A4|budget_tokens=512|blind,multi_hop,Qwen2.5-3B,0.475,0.325,0.625,40,0.47534A4|budget_tokens=512|blind,negation,Llama-3.2-3B,0.95,0.8875,1.0,80,0.012535A4|budget_tokens=512|blind,negation,Qwen2.5-3B,0.725,0.625,0.8125,80,0.17536A4|budget_tokens=512|blind,revision,Llama-3.2-3B,0.125,0.0625,0.2125,80,0.37537A4|budget_tokens=512|blind,revision,Qwen2.5-3B,0.2,0.1125,0.3,80,0.612538A4|budget_tokens=512|blind,temporal,Llama-3.2-3B,0.325,0.175,0.475,40,0.32539A4|budget_tokens=512|blind,temporal,Qwen2.5-3B,0.475,0.325,0.625,40,0.1540A4|budget_tokens=512|blind,unanswerable,Llama-3.2-3B,1.0,1.0,1.0,80,1.041A4|budget_tokens=512|blind,unanswerable,Qwen2.5-3B,1.0,1.0,1.0,80,1.042A4|budget_tokens=512|blind,unit_conversion,Llama-3.2-3B,0.025,0.0,0.075,40,0.57543A4|budget_tokens=512|blind,unit_conversion,Qwen2.5-3B,0.325,0.175,0.475,40,0.644A5|budget_tokens=512|blind,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.47545A5|budget_tokens=512|blind,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.32546A5|budget_tokens=512|blind,multi_hop,Llama-3.2-3B,0.1,0.025,0.2,40,0.947A5|budget_tokens=512|blind,multi_hop,Qwen2.5-3B,0.15,0.05,0.275,40,0.7548A5|budget_tokens=512|blind,negation,Llama-3.2-3B,0.5,0.375,0.6,80,0.37549A5|budget_tokens=512|blind,negation,Qwen2.5-3B,0.4875,0.36843750000000014,0.6,80,0.47550A5|budget_tokens=512|blind,revision,Llama-3.2-3B,0.075,0.025,0.15,80,0.837551A5|budget_tokens=512|blind,revision,Qwen2.5-3B,0.0375,0.0,0.1,80,0.8552A5|budget_tokens=512|blind,temporal,Llama-3.2-3B,0.1,0.025,0.2,40,0.8553A5|budget_tokens=512|blind,temporal,Qwen2.5-3B,0.075,0.0,0.175,40,0.854A5|budget_tokens=512|blind,unanswerable,Llama-3.2-3B,1.0,1.0,1.0,80,1.055A5|budget_tokens=512|blind,unanswerable,Qwen2.5-3B,1.0,1.0,1.0,80,1.056A5|budget_tokens=512|blind,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.7557A5|budget_tokens=512|blind,unit_conversion,Qwen2.5-3B,0.15,0.05,0.275,40,0.4558B2|bits=8,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.059B2|bits=8,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.060B2|bits=8,multi_hop,Llama-3.2-3B,1.0,1.0,1.0,40,0.061B2|bits=8,multi_hop,Qwen2.5-3B,1.0,1.0,1.0,40,0.062B2|bits=8,negation,Llama-3.2-3B,0.9,0.825,0.9625,80,0.063B2|bits=8,negation,Qwen2.5-3B,0.9375,0.8809375000000002,0.9875,80,0.064B2|bits=8,revision,Llama-3.2-3B,0.7625,0.675,0.85,80,0.065B2|bits=8,revision,Qwen2.5-3B,0.875,0.8125,0.9375,80,0.066B2|bits=8,temporal,Llama-3.2-3B,0.625,0.475,0.775,40,0.067B2|bits=8,temporal,Qwen2.5-3B,0.55,0.4,0.7,40,0.068B2|bits=8,unanswerable,Llama-3.2-3B,0.95,0.9,0.9875,80,0.9569B2|bits=8,unanswerable,Qwen2.5-3B,0.975,0.9375,1.0,80,0.97570B2|bits=8,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.071B2|bits=8,unit_conversion,Qwen2.5-3B,0.6,0.45,0.75,40,0.072B3|keep_frac=0.25,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.073B3|keep_frac=0.25,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.074B3|keep_frac=0.25,multi_hop,Llama-3.2-3B,0.15,0.05,0.275,40,0.27575B3|keep_frac=0.25,multi_hop,Qwen2.5-3B,0.175,0.075,0.3,40,0.176B3|keep_frac=0.25,negation,Llama-3.2-3B,0.725,0.65,0.8,80,0.077B3|keep_frac=0.25,negation,Qwen2.5-3B,0.9125,0.85,0.975,80,0.078B3|keep_frac=0.25,revision,Llama-3.2-3B,0.15,0.06843750000000012,0.2375,80,0.487579B3|keep_frac=0.25,revision,Qwen2.5-3B,0.1,0.025,0.1875,80,0.080B3|keep_frac=0.25,temporal,Llama-3.2-3B,0.575,0.425,0.725,40,0.081B3|keep_frac=0.25,temporal,Qwen2.5-3B,0.55,0.41187500000000027,0.7,40,0.082B3|keep_frac=0.25,unanswerable,Llama-3.2-3B,0.9375,0.875,0.9875,80,0.937583B3|keep_frac=0.25,unanswerable,Qwen2.5-3B,0.9875,0.9625,1.0,80,0.987584B3|keep_frac=0.25,unit_conversion,Llama-3.2-3B,0.025,0.0,0.075,40,0.6585B3|keep_frac=0.25,unit_conversion,Qwen2.5-3B,0.075,0.0,0.15,40,0.086B5|keep_frac=0.25|aware,aggregation,Llama-3.2-3B,0.0,0.0,0.0,40,0.087B5|keep_frac=0.25|aware,aggregation,Qwen2.5-3B,0.0,0.0,0.0,40,0.088B5|keep_frac=0.25|aware,multi_hop,Llama-3.2-3B,0.95,0.875,1.0,40,0.089B5|keep_frac=0.25|aware,multi_hop,Qwen2.5-3B,0.575,0.425,0.725,40,0.090B5|keep_frac=0.25|aware,negation,Llama-3.2-3B,0.85,0.7625,0.925,80,0.091B5|keep_frac=0.25|aware,negation,Qwen2.5-3B,0.9625,0.925,1.0,80,0.092B5|keep_frac=0.25|aware,revision,Llama-3.2-3B,0.7625,0.6875,0.8375,80,0.093B5|keep_frac=0.25|aware,revision,Qwen2.5-3B,0.275,0.175,0.375,80,0.094B5|keep_frac=0.25|aware,temporal,Llama-3.2-3B,0.7,0.55,0.85,40,0.095B5|keep_frac=0.25|aware,temporal,Qwen2.5-3B,0.55,0.4,0.7131249999999993,40,0.096B5|keep_frac=0.25|aware,unanswerable,Llama-3.2-3B,0.95,0.9,0.9875,80,0.9597B5|keep_frac=0.25|aware,unanswerable,Qwen2.5-3B,0.975,0.9375,1.0,80,0.97598B5|keep_frac=0.25|aware,unit_conversion,Llama-3.2-3B,0.0,0.0,0.0,40,0.099B5|keep_frac=0.25|aware,unit_conversion,Qwen2.5-3B,0.6,0.425,0.725,40,0.0100
Files · main
Menu

Theme