Upload 2 files

qbench_a1_pair_dev.csv

@@ -0,0 +1,13 @@
+Model (variant),Yes-or-No,What,How,Distortion,Other,Compare,Joint,Overall
+InfiMM (Zephyr-7B),48.11,39.04,40.06,42.56,43.78,41.77,48.33,42.95
+Emu2-Chat (LLaMA-33B),56.64,41.15,49.62,49.12,51.91,47.86,60,50.05
+Fuyu-8B (Persimmon-8B),68.76,33.56,38.78,46.83,54.03,47.86,55,49.15
+BakLLava (Mistral-7B),56.92,43.83,50,49.33,54.34,50.66,52.22,50.94
+mPLUG-Owl2 (Q-Instruct),59.19,42.12,47.43,49.63,52.48,49.81,53.88,50.54
+mPLUG-Owl2 (LLaMA-7B),58.43,39.72,48.39,49.04,51.55,47.5,60.55,49.85
+LLaVA-v1.5 (Vicuna-v1.5-7B),60.46,42.85,41.53,47.88,51.89,46.55,59.57,49.32
+LLaVA-v1.5 (Vicuna-v1.5-13B),56.42,42.46,48.38,48.15,53.41,48.84,54.44,49.85
+Qwen-VL-Plus (Close-Source),63.63,55.55,55.71,61.61,56.52,65.81,58.45,60.7
+Qwen-VL-Max (Close-Source),71.96,62.87,65.53,69.21,62.69,67.54,66.01,67.27
+Gemini-Pro (Close-Source),64.98,51.36,54.16,58.17,56.52,57.73,57.22,57.64
+GPT-4V (Close-Source),79.34,70.54,78.52,75.84,77.95,78.8,66.11,76.52

qbench_a1_pair_test.csv

@@ -0,0 +1,13 @@
+Model (variant),Yes-or-No,What,How,Distortion,Other,Compare,Joint,Overall
+InfiMM (Zephyr-7B),54.21,43.38,45.32,49.57,45.67,48.32,48.88,48.44
+Emu2-Chat (LLaMA-33B),51.94,29.78,53.84,42.01,55.71,46.26,49.09,47.08
+Fuyu-8B (Persimmon-8B),70.36,28.13,35.98,44.08,57.43,47.02,51.11,47.94
+BakLLava (Mistral-7B),60.09,45.42,50.86,53.09,58.82,54.52,55.55,52.75
+mPLUG-Owl2 (Q-Instruct),60.24,47.46,48.78,52.81,53.97,51.42,59.11,53.15
+mPLUG-Owl2 (LLaMA-7B),58.07,36.61,48.44,47.74,51.9,45.73,60,48.94
+LLaVA-v1.5 (Vicuna-v1.5-7B),60.72,42.37,50.17,49.15,59.86,52.97,49.77,52.25
+LLaVA-v1.5 (Vicuna-v1.5-13B),57.34,47.45,49.13,49.01,59.51,52.06,52,52.05
+Qwen-VL-Plus (Close-Source),66.85,55.79,59.91,62.46,58.77,62.17,59.2,61.48
+Qwen-VL-Max (Close-Source),67.65,67.56,65.35,69.09,61.18,68.65,61.29,66.99
+Gemini-Pro (Close-Source),65.78,56.61,56.74,60.42,60.55,60.46,60.44,60.46
+GPT-4V (Close-Source),79.75,69.49,84.42,77.32,79.93,81,68,78.07