Sam Heutmaker
commited on
Commit
·
5efb017
1
Parent(s):
0d7a0bc
update readme
Browse files
README.md
CHANGED
|
@@ -87,6 +87,8 @@ Performance metrics on our internal evaluation set:
|
|
| 87 |
| claude_4_sonnet | 3.16 | 0.463 | 0.179 | 0.281 | 0.060 |
|
| 88 |
| gpt_4.1 | 3.64 | 0.581 | 0.260 | 0.376 | 0.119 |
|
| 89 |
|
|
|
|
|
|
|
| 90 |
<img src="./assets/judge-score.png" alt="Average Judge Score Comparison" width="100%" />
|
| 91 |
|
| 92 |
|
|
|
|
| 87 |
| claude_4_sonnet | 3.16 | 0.463 | 0.179 | 0.281 | 0.060 |
|
| 88 |
| gpt_4.1 | 3.64 | 0.581 | 0.260 | 0.376 | 0.119 |
|
| 89 |
|
| 90 |
+
We used Gemini-2.5-Pro as the judge model, which ranks ClipTagger-12b roughly equal to GPT-4.1, and better than Claude 4 Sonnet.
|
| 91 |
+
|
| 92 |
<img src="./assets/judge-score.png" alt="Average Judge Score Comparison" width="100%" />
|
| 93 |
|
| 94 |
|