[Auto] Update leaderboard scores
Browse files- leaderboard_data.json +37 -5
leaderboard_data.json
CHANGED
|
@@ -9,10 +9,42 @@
|
|
| 9 |
"track": "Standard",
|
| 10 |
"date": "2026-02-12",
|
| 11 |
"overall_em": 9.8,
|
| 12 |
-
"overall_f1": 34.
|
| 13 |
-
"intra_em":
|
| 14 |
-
"intra_f1":
|
| 15 |
-
"inter_em":
|
| 16 |
-
"inter_f1":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
| 18 |
]
|
|
|
|
| 9 |
"track": "Standard",
|
| 10 |
"date": "2026-02-12",
|
| 11 |
"overall_em": 9.8,
|
| 12 |
+
"overall_f1": 34.3,
|
| 13 |
+
"intra_em": 12.3,
|
| 14 |
+
"intra_f1": 39.5,
|
| 15 |
+
"inter_em": 7.7,
|
| 16 |
+
"inter_f1": 29.8
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"method": "ImageSeeker(Qwen3-VL-235b-A22b-Instruct)",
|
| 20 |
+
"url": "https://github.com/RUC-NLPIR/DeepImageSearch",
|
| 21 |
+
"org": "RUC-NLPIR",
|
| 22 |
+
"agent": "ImageSeeker",
|
| 23 |
+
"backbone": "Qwen3-VL-235b-A22b-Instruct",
|
| 24 |
+
"retriever": "Qwen3-VL-Embedding-8B",
|
| 25 |
+
"track": "Standard",
|
| 26 |
+
"date": "2026-02-12",
|
| 27 |
+
"overall_em": 11.5,
|
| 28 |
+
"overall_f1": 27.2,
|
| 29 |
+
"intra_em": 17.5,
|
| 30 |
+
"intra_f1": 32.1,
|
| 31 |
+
"inter_em": 6.2,
|
| 32 |
+
"inter_f1": 22.9
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"method": "ImageSeeker(Qwen3-VL-235b-A22b-Thinking)",
|
| 36 |
+
"url": "https://github.com/RUC-NLPIR/DeepImageSearch",
|
| 37 |
+
"org": "RUC-NLPIR",
|
| 38 |
+
"agent": "ImageSeeker",
|
| 39 |
+
"backbone": "Qwen3-VL-235b-A22b-Thinking",
|
| 40 |
+
"retriever": "Qwen3-VL-Embedding-8B",
|
| 41 |
+
"track": "Standard",
|
| 42 |
+
"date": "2026-02-12",
|
| 43 |
+
"overall_em": 8.2,
|
| 44 |
+
"overall_f1": 20.4,
|
| 45 |
+
"intra_em": 12.3,
|
| 46 |
+
"intra_f1": 23.7,
|
| 47 |
+
"inter_em": 4.6,
|
| 48 |
+
"inter_f1": 17.6
|
| 49 |
}
|
| 50 |
]
|