OrlandoHugBot commited on
Commit
9d30f23
·
verified ·
1 Parent(s): 6994468

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -67
README.md CHANGED
@@ -30,72 +30,21 @@ license: mit
30
  <br>
31
  <br>
32
  <div align="center">
33
- <b>Comparison with Larger-Scale Open-Source and Closed-Source Models</b>
 
 
 
 
34
  </div>
35
 
36
- <table align="center">
37
- <thead>
38
- <tr>
39
- <th></th>
40
- <th align="center"><strong>Benchmark</strong></th>
41
- <th align="center"><strong>LLM</strong></th>
42
- <th align="center" colspan="4"><strong>VLM</strong></th>
43
- </tr>
44
- <tr>
45
- <th></th>
46
- <th></th>
47
- <th align="center"><strong>QwQ-32B-Preview</strong></th>
48
- <th align="center"><strong>InternVL-2.5-38B</strong></th>
49
- <th align="center"><strong>VILA 1.5-40B</strong></th>
50
- <th align="center"><strong>InternVL2-40B</strong></th>
51
- <th align="center"><strong>Skywork-R1V-38B</strong></th>
52
- </tr>
53
- </thead>
54
- <tbody>
55
- <tr>
56
- <td rowspan="3">Reasoning</td>
57
- <td>MATH-500</td>
58
- <td align="center">90.6</td>
59
- <td align="center">-</td>
60
- <td align="center">-</td>
61
- <td align="center">-</td>
62
- <td align="center"><strong>94.0</strong></td>
63
- </tr>
64
- <tr>
65
- <td>AIME 2024</td>
66
- <td align="center">50.0</td>
67
- <td align="center">-</td>
68
- <td align="center">-</td>
69
- <td align="center">-</td>
70
- <td align="center"><strong>72.0</strong></td>
71
- </tr>
72
- <tr>
73
- <td>GPQA</td>
74
- <td align="center">54.5</td>
75
- <td align="center">-</td>
76
- <td align="center">-</td>
77
- <td align="center">-</td>
78
- <td align="center"><strong>61.6</strong></td>
79
- </tr>
80
- <tr>
81
- <td rowspan="3">Vision</td>
82
- <td>MathVista(mini)</td>
83
- <td align="center">-</td>
84
- <td align="center">71.9</td>
85
- <td align="center">49.5</td>
86
- <td align="center">63.7</td>
87
- <td align="center">67.5</td>
88
- </tr>
89
- <tr>
90
- <td>MMMU(Val)</td>
91
- <td align="center">-</td>
92
- <td align="center">63.9</td>
93
- <td align="center">55.1</td>
94
- <td align="center">55.2</td>
95
- <td align="center"><strong>69.0</strong></td>
96
- </tr>
97
- </tbody>
98
- </table>
99
 
100
 
101
  <br>
@@ -233,9 +182,6 @@ license: mit
233
  </tbody>
234
  </table>
235
 
236
- <div align="center">
237
- <img src="eval.jpeg" width="90%" height="90%" alt="skywork_r1v_eval" />
238
- </div>
239
 
240
  ---
241
 
 
30
  <br>
31
  <br>
32
  <div align="center">
33
+ <b>Comparison with Larger-Scale Open-Source Models</b>
34
+ </div>
35
+
36
+ <div align="center">
37
+ <img src="open_source.png" width="100%" height="100%" alt="skywork_r1v2_eval_open" />
38
  </div>
39
 
40
+
41
+ <div align="center">
42
+ <b>Comparison with Properitary Models</b>
43
+ </div>
44
+
45
+ <div align="center">
46
+ <img src="properitary.png" width="100%" height="100%" alt="skywork_r1v2_eval_properitary" />
47
+ </div>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  <br>
 
182
  </tbody>
183
  </table>
184
 
 
 
 
185
 
186
  ---
187