arsh-maincode commited on
Commit
3dd1a9d
·
verified ·
1 Parent(s): 1f25c5a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -33,15 +33,15 @@ See [TEST_REPORT.json](TEST_REPORT.json). These checks are not a full benchmark
33
 
34
  ## Results
35
 
36
- Evaluated with Decision Index 0.2.1 over 150,317 requests (currently awaiting official submission).
37
 
38
  | Model | Parameters | Decision Index | Raw | Breadth |
39
  |---|---:|---:|---:|---:|
40
- | Matilda-Jev | 26.1B | 59.59 | 69.18 | 58.39 |
41
 
42
  | Knowledge & Reasoning | Language | Retrieval & Classification | Tools & Automation | Arts & Human Taste |
43
  |---:|---:|---:|---:|---:|
44
- | 44.09 | 66.27 | 61.07 | 79.07 | 43.85 |
45
 
46
  Area scores are chance-corrected skill multiplied by 100.
47
 
 
33
 
34
  ## Results
35
 
36
+ Evaluated with Decision Index 0.3 (public) over 150,317 requests (currently awaiting official submission).
37
 
38
  | Model | Parameters | Decision Index | Raw | Breadth |
39
  |---|---:|---:|---:|---:|
40
+ | Matilda-Jev | 26.1B | 60.16 | 70.04 | 59.21 |
41
 
42
  | Knowledge & Reasoning | Language | Retrieval & Classification | Tools & Automation | Arts & Human Taste |
43
  |---:|---:|---:|---:|---:|
44
+ | 46.84 | 64.80 | 61.07 | 79.07 | 46.22 |
45
 
46
  Area scores are chance-corrected skill multiplied by 100.
47