Update README.md
Browse files
README.md
CHANGED
@@ -55,43 +55,43 @@ InternVL 2.5is a multimodal large language model series, featuring models of var
|
|
55 |
|
56 |
| Benchmark | GPT-4V | GPT-4o-20240513 | Claude-3-Opus | Claude-3.5-Sonnet | Gemini-1.5-Pro | LLaVA-OneVision-72B | Qwen2-VL-72B | InternVL2.5-78B |
|
57 |
|----------------------------|-------------|-----------------|---------------|-------------------|----------------|---------------------|--------------|-----------------|
|
58 |
-
| MMMU
|
59 |
-
| MMMU
|
60 |
-
| MMMU-PRO
|
61 |
-
| MathVista
|
62 |
-
|
|
63 |
-
| MathVision
|
64 |
-
| MathVerse
|
65 |
| Olympiad Bench | 18.0 | 25.9 | - | - | - | - | - | 11.6 |
|
66 |
-
| AI2D
|
67 |
-
| ChartQA
|
68 |
-
| TextVQA
|
69 |
-
| DocVQA
|
70 |
-
| InfoVQA
|
71 |
| OCR-Bench | 645 | 736 | 694 | 788 | 754 | 741 | 877 | 854 |
|
72 |
| SEED-2 Plus | 53.8 | 72.0 | 44.2 | 71.7 | - | 69.7 | - | 71.3 |
|
73 |
-
| CharXiv
|
74 |
-
| VCR-EN-Easy
|
75 |
-
| BLINK
|
76 |
| Mantis Eval | 62.7 | - | - | - | - | 77.6 | - | 77.0 |
|
77 |
| MMIU | - | 55.7 | - | 53.4 | 53.4 | - | - | 55.8 |
|
78 |
| Muir Bench | 62.3 | 68.0 | - | - | - | 54.8 | - | 63.5 |
|
79 |
-
| MMT
|
80 |
-
| MIRB
|
81 |
| RealWorld QA | 61.4 | 75.4 | - | 60.1 | 67.5 | 71.9 | 77.8 | 78.7 |
|
82 |
-
| MME-RW
|
83 |
-
| WildVision
|
84 |
| R-Bench | 65.6 | 77.7 | - | - | - | - | - | 77.2 |
|
85 |
-
| MME
|
86 |
-
| MMB
|
87 |
-
| MMBv1.1
|
88 |
-
| MMVet
|
89 |
-
| MMVetv2
|
90 |
| MMStar | 56.0 | 64.7 | 45.7 | 65.1 | 59.1 | 65.8 | 68.3 | 69.5 |
|
91 |
-
| HallBench
|
92 |
-
| MMHal
|
93 |
-
| CRPE
|
94 |
-
| POPE
|
95 |
|
96 |
|
97 |
### Video Benchmarks
|
|
|
55 |
|
56 |
| Benchmark | GPT-4V | GPT-4o-20240513 | Claude-3-Opus | Claude-3.5-Sonnet | Gemini-1.5-Pro | LLaVA-OneVision-72B | Qwen2-VL-72B | InternVL2.5-78B |
|
57 |
|----------------------------|-------------|-----------------|---------------|-------------------|----------------|---------------------|--------------|-----------------|
|
58 |
+
| MMMU<sub>val<sub> | 63.1 | 69.1 | - | 68.3 | 62.2 | 56.8 | 64.5 | 70.1 |
|
59 |
+
| MMMU<sub>test<sub> | - | - | - | - | - | - | - | 61.8 |
|
60 |
+
| MMMU-PRO<sub>overall<sub> | - | 51.9 | - | 51.5 | 46.9 | 31.0 | 46.2 | 48.6 |
|
61 |
+
| MathVista<sub>mini<sub> | 58.1 | 63.8 | - | 67.7 | 63.9 | 67.5 | 70.5 | 72.3 |
|
62 |
+
| MathVisionv<sub>mini<sub> | - | - | - | - | - | - | - | 34.9 |
|
63 |
+
| MathVision<sub>full<sub> | 24.0 | 30.4 | - | - | 19.2 | - | 25.9 | 32.2 |
|
64 |
+
| MathVerse<sub>mini<sub> | 32.8 | 50.2 | - | - | - | 39.1 | - | 51.7 |
|
65 |
| Olympiad Bench | 18.0 | 25.9 | - | - | - | - | - | 11.6 |
|
66 |
+
| AI2D<sub>w / wo M<sub> | 78.2 / 89.4 | 84.6 / 94.2 | 70.6 / 88.1 | 81.2 / 94.7 | 79.1 / 94.4 | 85.6 / - | 88.1 / - | 89.1 / 95.7 |
|
67 |
+
| ChartQA<sub>test avg.<sub> | 78.5 | 85.7 | 80.8 | 90.8 | 87.2 | 83.7 | 88.3 | 88.3 |
|
68 |
+
| TextVQA<sub>val<sub> | 78.0 | 77.4 | 67.5 | 74.1 | 78.8 | 80.5 | 85.5 | 83.4 |
|
69 |
+
| DocVQA<sub>test<sub> | 88.4 | 92.8 | 89.3 | 95.2 | 93.1 | 91.3 | 96.5 | 95.1 |
|
70 |
+
| InfoVQA<sub>test<sub> | 75.1 | 79.2 | 55.6 | 74.3 | 81.0 | 74.9 | 84.5 | 84.1 |
|
71 |
| OCR-Bench | 645 | 736 | 694 | 788 | 754 | 741 | 877 | 854 |
|
72 |
| SEED-2 Plus | 53.8 | 72.0 | 44.2 | 71.7 | - | 69.7 | - | 71.3 |
|
73 |
+
| CharXiv<sub>RQ / DQ<sub> | 37.1 / 79.9 | 47.1 / 84.5 | 30.2 / 71.6 | 60.2 / 84.3 | 43.3 / 72.0 | - | 91.3 / 94.6 | 42.4 / 82.3 |
|
74 |
+
| VCR-EN-Easy<sub>EM / Jaccard<sub> | 52.0 / 65.4 | 91.6 / 96.4 | 62.0 / 77.7 | 63.9 / 74.7 | 62.7 / 77.7 | - | 94.6 | 95.7 / 94.5 |
|
75 |
+
| BLINK<sub>val<sub> | 54.6 | 68.0 | - | - | - | 55.4 | - | 63.8 |
|
76 |
| Mantis Eval | 62.7 | - | - | - | - | 77.6 | - | 77.0 |
|
77 |
| MMIU | - | 55.7 | - | 53.4 | 53.4 | - | - | 55.8 |
|
78 |
| Muir Bench | 62.3 | 68.0 | - | - | - | 54.8 | - | 63.5 |
|
79 |
+
| MMT<sub>val<sub> | 64.3 | 65.4 | - | - | 64.5 | - | 71.8 | 70.8 |
|
80 |
+
| MIRB<sub>avg.<sub> | 53.1 | - | - | - | - | - | - | 61.1 |
|
81 |
| RealWorld QA | 61.4 | 75.4 | - | 60.1 | 67.5 | 71.9 | 77.8 | 78.7 |
|
82 |
+
| MME-RW<sub>EN<sub> | - | 45.2 | - | 51.6 | 38.2 | - | - | 62.9 |
|
83 |
+
| WildVision<sub>win rate<sub> | 71.8 | 80.6 | - | - | - | - | - | 71.4 |
|
84 |
| R-Bench | 65.6 | 77.7 | - | - | - | - | - | 77.2 |
|
85 |
+
| MME<sub>sum<sub> | 1926.6 | -- | 1586.8 | -- | -- | 2261.0 | 2482.7 | 2494.5 |
|
86 |
+
| MMB<sub>EN / CN<sub> | 81.0 / 80.2 | 83.4 / 82.1 | 63.3 / 59.2 | 82.6 / 83.5 | 73.9 / 73.8 | 85.8 / 85.3 | 86.5 / 86.6 | 88.3 / 88.5 |
|
87 |
+
| MMBv1.1<sub>EN<sub> | 80.0 | 83.1 | 60.1 | 80.9 | 74.6 | 85.0 | 85.9 | 87.4 |
|
88 |
+
| MMVet<sub>turbo<sub> | 67.5 | 69.1 | 51.7 | 70.1 | 64.0 | 60.6 | 74.0 | 72.3 |
|
89 |
+
| MMVetv2<sub>0613<sub> | 66.3 | 71.0 | 55.8 | 71.8 | 66.9 | -- | 66.9 | 65.5 |
|
90 |
| MMStar | 56.0 | 64.7 | 45.7 | 65.1 | 59.1 | 65.8 | 68.3 | 69.5 |
|
91 |
+
| HallBench<sub>avg.<sub> | 46.5 | 55.0 | 37.8 | 55.5 | 45.6 | 49.0 | 58.1 | 57.4 |
|
92 |
+
| MMHal<sub>score<sub> | -- | 4.00 | -- | -- | -- | -- | -- | 3.89 |
|
93 |
+
| CRPE<sub>relation<sub> | -- | 76.6 | -- | -- | -- | -- | -- | 78.8 |
|
94 |
+
| POPE<sub>avg.<sub> | -- | 86.9 | -- | -- | -- | -- | -- | 90.8 |
|
95 |
|
96 |
|
97 |
### Video Benchmarks
|