khang119966 commited on
Commit
7bea5e4
β€’
1 Parent(s): 78869f1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -76,6 +76,26 @@ Since there are still many different metrics that need to be tested, **we chose
76
  </tr>
77
  </table>
78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  We are still working on more detailed benchmarks.
80
 
81
  ## Examples
 
76
  </tr>
77
  </table>
78
 
79
+ The benchmark result in [MTVQA](https://github.com/bytedance/MTVQA/tree/main)
80
+
81
+ | Models | Open-Source | Vietnamese Score |
82
+ |:----------------------------------:|:-------------:|:------------------:|
83
+ | Qwen2-VL 72B (Top1) | βœ— | 41.6 |
84
+ | GPT-4o (Top2) | βœ— | 34.2 |
85
+ | **Vintern-1B-V2** (Top3) | βœ“ | **31.7** |
86
+ | Qwen2-VL 7B | βœ“ | 30.0 |
87
+ | Claude3 Opus | βœ— | 29.1 |
88
+ | GPT-4o mini | βœ— | 29.1 |
89
+ | GPT-4V | βœ— | 28.9 |
90
+ | Vintern-1B-V3 | βœ“ | 28.7 |
91
+ | Gemini Ultra | βœ— | 28.6 |
92
+ | InternVL2 76B | βœ“ | 26.9 |
93
+ | QwenVL Max | βœ— | 23.5 |
94
+ | Claude3 Sonnet | βœ— | 20.8 |
95
+ | QwenVL Plus | βœ— | 18.1 |
96
+ | MiniCPM-V2.5 | βœ“ | 15.3 |
97
+ | InternVL-V1.5 | βœ— | 12.4 |
98
+
99
  We are still working on more detailed benchmarks.
100
 
101
  ## Examples