Upload visitbench_leaderboard_Single~Image_Sep252023.tsv

visitbench_leaderboard_Single~Image_Sep252023.tsv

@@ -0,0 +1,16 @@
+Category	Model	Elo	# Matches	Win vs. Reference (w/ # ratings)
+Single Image	human_verified_reference	1382	5880	---
+Single Image	llava-a1-predictions	1203	678	35.07% (n=134)
+Single Image	llava13b_output	1095	5420	18.53% (n=475)
+Single Image	mPLUG-Owl prediction	1087	5440	15.83% (n=480)
+Single Image	LlamaAdapter-v2 prediction	1066	5469	14.14% (n=488)
+Single Image	Lynx(8B) predictions	1037	787	11.43% (n=140)
+Single Image	idefics9b_prediction	1020	794	9.72% (n=144)
+Single Image	instruct_blip_output	1000	5469	14.12% (n=503)
+Single Image	otter	962	5443	7.01% (n=499)
+Single Image	visual_gpt_davinci003_output	941	5437	1.57% (n=510)
+Single Image	MiniGPT-4 prediction	926	5448	3.36% (n=506)
+Single Image	Octopus V2 prediction	925	790	8.90% (n=146)
+Single Image	openflamingo	851	5479	2.95% (n=509)
+Single Image	panda_gpt_13b_output	775	5465	2.70% (n=519)
+Single Image	mmgpt_output	731	5471	0.19% (n=527)