bluelike commited on
Commit
77c8a84
1 Parent(s): 33cac37

add vcr results

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -52,13 +52,15 @@ We have three models with 2, 7 and 72 billion parameters. This repo contains the
52
 
53
  | Benchmark | InternVL2-2B | MiniCPM-V 2.0 | **Qwen2-VL-2B** |
54
  | :--- | :---: | :---: | :---: |
 
55
  | DocVQA<sub>test</sub> | 86.9 | - | **90.1** |
56
  | InfoVQA<sub>test</sub> | 58.9 | - | **65.5** |
57
  | ChartQA<sub>test</sub> | **76.2** | - | 73.5 |
58
  | TextVQA<sub>val</sub> | 73.4 | - | **79.7** |
59
  | OCRBench | 781 | 605 | **794** |
60
  | MTVQA | - | - | **20.0** |
61
- | MMMU<sub>val</sub> | 36.3 | 38.2 | **41.1** |
 
62
  | RealWorldQA | 57.3 | 55.8 | **62.9** |
63
  | MME<sub>sum</sub> | **1876.8** | 1808.6 | 1872.0 |
64
  | MMBench-EN<sub>test</sub> | 73.2 | 69.1 | **74.9** |
 
52
 
53
  | Benchmark | InternVL2-2B | MiniCPM-V 2.0 | **Qwen2-VL-2B** |
54
  | :--- | :---: | :---: | :---: |
55
+ | MMMU<sub>val</sub> | 36.3 | 38.2 | **41.1** |
56
  | DocVQA<sub>test</sub> | 86.9 | - | **90.1** |
57
  | InfoVQA<sub>test</sub> | 58.9 | - | **65.5** |
58
  | ChartQA<sub>test</sub> | **76.2** | - | 73.5 |
59
  | TextVQA<sub>val</sub> | 73.4 | - | **79.7** |
60
  | OCRBench | 781 | 605 | **794** |
61
  | MTVQA | - | - | **20.0** |
62
+ | VCR<sub>en easy</sub> | - | - | **81.45**
63
+ | VCR<sub>zh easy</sub> | - | - | **46.16**
64
  | RealWorldQA | 57.3 | 55.8 | **62.9** |
65
  | MME<sub>sum</sub> | **1876.8** | 1808.6 | 1872.0 |
66
  | MMBench-EN<sub>test</sub> | 73.2 | 69.1 | **74.9** |