yonatanbitton commited on
Commit
9b245db
1 Parent(s): de56a0d

Update visitbench_leaderboard_Single~Image_Sep252023.tsv

Browse files
visitbench_leaderboard_Single~Image_Sep252023.tsv CHANGED
@@ -1,8 +1,8 @@
1
  Category Model Elo # Matches Win vs. Reference (w/ # ratings)
2
  Single Image Human Verified Reference 1382 5880 ---
3
- Single Image LLaVA-Plus (13B) 1203 678 35.07% (n=134)
4
- Single Image LLaVA (13B) 1095 5420 18.53% (n=475)
5
- Single Image mPLUG-Owl 1087 5440 15.83% (n=480)
6
  Single Image LlamaAdapter-v2 1066 5469 14.14% (n=488)
7
  Single Image Lynx(8B) 1037 787 11.43% (n=140)
8
  Single Image idefics (9B) 1020 794 9.72% (n=144)
 
1
  Category Model Elo # Matches Win vs. Reference (w/ # ratings)
2
  Single Image Human Verified Reference 1382 5880 ---
3
+ Single Image LLaVA-Plus (13B) 🥇 1203 678 35.07% (n=134)
4
+ Single Image LLaVA (13B) 🥈 1095 5420 18.53% (n=475)
5
+ Single Image mPLUG-Owl 🥉 1087 5440 15.83% (n=480)
6
  Single Image LlamaAdapter-v2 1066 5469 14.14% (n=488)
7
  Single Image Lynx(8B) 1037 787 11.43% (n=140)
8
  Single Image idefics (9B) 1020 794 9.72% (n=144)