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)
|