[Auto] Update leaderboard scores
Browse files- leaderboard_data.json +10 -10
leaderboard_data.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"backbone": "Qwen3-VL-235b-A22b-Instruct",
|
| 8 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 9 |
"track": "Standard",
|
| 10 |
-
"date": "2026-08-
|
| 11 |
"overall_em": 11.5,
|
| 12 |
"overall_f1": 27.2,
|
| 13 |
"intra_em": 17.5,
|
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"backbone": "Gemini-3-Flash-Preview",
|
| 24 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 25 |
"track": "Standard",
|
| 26 |
-
"date": "2026-08-
|
| 27 |
"overall_em": 12.3,
|
| 28 |
"overall_f1": 36.8,
|
| 29 |
"intra_em": 15.8,
|
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"backbone": "Qwen3-VL-235b-A22b-Thinking",
|
| 40 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 41 |
"track": "Standard",
|
| 42 |
-
"date": "2026-08-
|
| 43 |
"overall_em": 8.2,
|
| 44 |
"overall_f1": 20.4,
|
| 45 |
"intra_em": 12.3,
|
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"backbone": "Qwen3-VL-32b-Instruct",
|
| 56 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 57 |
"track": "Standard",
|
| 58 |
-
"date": "2026-08-
|
| 59 |
"overall_em": 8.2,
|
| 60 |
"overall_f1": 20.9,
|
| 61 |
"intra_em": 14.0,
|
|
@@ -71,7 +71,7 @@
|
|
| 71 |
"backbone": "Gpt-4o",
|
| 72 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 73 |
"track": "Standard",
|
| 74 |
-
"date": "2026-08-
|
| 75 |
"overall_em": 5.7,
|
| 76 |
"overall_f1": 21.8,
|
| 77 |
"intra_em": 5.3,
|
|
@@ -87,7 +87,7 @@
|
|
| 87 |
"backbone": "Glm-4.6v",
|
| 88 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 89 |
"track": "Standard",
|
| 90 |
-
"date": "2026-08-
|
| 91 |
"overall_em": 8.2,
|
| 92 |
"overall_f1": 26.1,
|
| 93 |
"intra_em": 10.5,
|
|
@@ -103,7 +103,7 @@
|
|
| 103 |
"backbone": "Claude-Opus-4-5-20251101",
|
| 104 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 105 |
"track": "Standard",
|
| 106 |
-
"date": "2026-08-
|
| 107 |
"overall_em": 28.7,
|
| 108 |
"overall_f1": 55.0,
|
| 109 |
"intra_em": 35.1,
|
|
@@ -119,7 +119,7 @@
|
|
| 119 |
"backbone": "Claude-Sonnet-4-5-20250929",
|
| 120 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 121 |
"track": "Standard",
|
| 122 |
-
"date": "2026-08-
|
| 123 |
"overall_em": 22.1,
|
| 124 |
"overall_f1": 43.8,
|
| 125 |
"intra_em": 28.1,
|
|
@@ -135,7 +135,7 @@
|
|
| 135 |
"backbone": "Gpt-5.2",
|
| 136 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 137 |
"track": "Standard",
|
| 138 |
-
"date": "2026-08-
|
| 139 |
"overall_em": 13.1,
|
| 140 |
"overall_f1": 30.0,
|
| 141 |
"intra_em": 19.3,
|
|
@@ -151,7 +151,7 @@
|
|
| 151 |
"backbone": "Gemini-3-Pro-Preview",
|
| 152 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 153 |
"track": "Standard",
|
| 154 |
-
"date": "2026-08-
|
| 155 |
"overall_em": 24.6,
|
| 156 |
"overall_f1": 47.9,
|
| 157 |
"intra_em": 29.8,
|
|
|
|
| 7 |
"backbone": "Qwen3-VL-235b-A22b-Instruct",
|
| 8 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 9 |
"track": "Standard",
|
| 10 |
+
"date": "2026-08-10",
|
| 11 |
"overall_em": 11.5,
|
| 12 |
"overall_f1": 27.2,
|
| 13 |
"intra_em": 17.5,
|
|
|
|
| 23 |
"backbone": "Gemini-3-Flash-Preview",
|
| 24 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 25 |
"track": "Standard",
|
| 26 |
+
"date": "2026-08-10",
|
| 27 |
"overall_em": 12.3,
|
| 28 |
"overall_f1": 36.8,
|
| 29 |
"intra_em": 15.8,
|
|
|
|
| 39 |
"backbone": "Qwen3-VL-235b-A22b-Thinking",
|
| 40 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 41 |
"track": "Standard",
|
| 42 |
+
"date": "2026-08-10",
|
| 43 |
"overall_em": 8.2,
|
| 44 |
"overall_f1": 20.4,
|
| 45 |
"intra_em": 12.3,
|
|
|
|
| 55 |
"backbone": "Qwen3-VL-32b-Instruct",
|
| 56 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 57 |
"track": "Standard",
|
| 58 |
+
"date": "2026-08-10",
|
| 59 |
"overall_em": 8.2,
|
| 60 |
"overall_f1": 20.9,
|
| 61 |
"intra_em": 14.0,
|
|
|
|
| 71 |
"backbone": "Gpt-4o",
|
| 72 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 73 |
"track": "Standard",
|
| 74 |
+
"date": "2026-08-10",
|
| 75 |
"overall_em": 5.7,
|
| 76 |
"overall_f1": 21.8,
|
| 77 |
"intra_em": 5.3,
|
|
|
|
| 87 |
"backbone": "Glm-4.6v",
|
| 88 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 89 |
"track": "Standard",
|
| 90 |
+
"date": "2026-08-10",
|
| 91 |
"overall_em": 8.2,
|
| 92 |
"overall_f1": 26.1,
|
| 93 |
"intra_em": 10.5,
|
|
|
|
| 103 |
"backbone": "Claude-Opus-4-5-20251101",
|
| 104 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 105 |
"track": "Standard",
|
| 106 |
+
"date": "2026-08-10",
|
| 107 |
"overall_em": 28.7,
|
| 108 |
"overall_f1": 55.0,
|
| 109 |
"intra_em": 35.1,
|
|
|
|
| 119 |
"backbone": "Claude-Sonnet-4-5-20250929",
|
| 120 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 121 |
"track": "Standard",
|
| 122 |
+
"date": "2026-08-10",
|
| 123 |
"overall_em": 22.1,
|
| 124 |
"overall_f1": 43.8,
|
| 125 |
"intra_em": 28.1,
|
|
|
|
| 135 |
"backbone": "Gpt-5.2",
|
| 136 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 137 |
"track": "Standard",
|
| 138 |
+
"date": "2026-08-10",
|
| 139 |
"overall_em": 13.1,
|
| 140 |
"overall_f1": 30.0,
|
| 141 |
"intra_em": 19.3,
|
|
|
|
| 151 |
"backbone": "Gemini-3-Pro-Preview",
|
| 152 |
"retriever": "Qwen3-VL-Embedding-8B",
|
| 153 |
"track": "Standard",
|
| 154 |
+
"date": "2026-08-10",
|
| 155 |
"overall_em": 24.6,
|
| 156 |
"overall_f1": 47.9,
|
| 157 |
"intra_em": 29.8,
|