Update README.md
Browse files
README.md
CHANGED
|
@@ -1,113 +1,4 @@
|
|
| 1 |
-
|
| 2 |
-
metrics:
|
| 3 |
-
- name: pass@1
|
| 4 |
-
type: pass@1
|
| 5 |
-
value: 0.3155
|
| 6 |
-
verified: false
|
| 7 |
-
- task:
|
| 8 |
-
type: text-generation
|
| 9 |
-
dataset:
|
| 10 |
-
type: nuprl/MultiPL-E
|
| 11 |
-
name: MultiPL-HumanEval (C#)
|
| 12 |
-
metrics:
|
| 13 |
-
- name: pass@1
|
| 14 |
-
type: pass@1
|
| 15 |
-
value: 0.2101
|
| 16 |
-
verified: false
|
| 17 |
-
- task:
|
| 18 |
-
type: text-generation
|
| 19 |
-
dataset:
|
| 20 |
-
type: nuprl/MultiPL-E
|
| 21 |
-
name: MultiPL-HumanEval (D)
|
| 22 |
-
metrics:
|
| 23 |
-
- name: pass@1
|
| 24 |
-
type: pass@1
|
| 25 |
-
value: 0.1357
|
| 26 |
-
verified: false
|
| 27 |
-
- task:
|
| 28 |
-
type: text-generation
|
| 29 |
-
dataset:
|
| 30 |
-
type: nuprl/MultiPL-E
|
| 31 |
-
name: MultiPL-HumanEval (Go)
|
| 32 |
-
metrics:
|
| 33 |
-
- name: pass@1
|
| 34 |
-
type: pass@1
|
| 35 |
-
value: 0.1761
|
| 36 |
-
verified: false
|
| 37 |
-
- task:
|
| 38 |
-
type: text-generation
|
| 39 |
-
dataset:
|
| 40 |
-
type: nuprl/MultiPL-E
|
| 41 |
-
name: MultiPL-HumanEval (Java)
|
| 42 |
-
metrics:
|
| 43 |
-
- name: pass@1
|
| 44 |
-
type: pass@1
|
| 45 |
-
value: 0.3022
|
| 46 |
-
verified: false
|
| 47 |
-
- task:
|
| 48 |
-
type: text-generation
|
| 49 |
-
dataset:
|
| 50 |
-
type: nuprl/MultiPL-E
|
| 51 |
-
name: MultiPL-HumanEval (Julia)
|
| 52 |
-
metrics:
|
| 53 |
-
- name: pass@1
|
| 54 |
-
type: pass@1
|
| 55 |
-
value: 0.2302
|
| 56 |
-
verified: false
|
| 57 |
-
- task:
|
| 58 |
-
type: text-generation
|
| 59 |
-
dataset:
|
| 60 |
-
type: nuprl/MultiPL-E
|
| 61 |
-
name: MultiPL-HumanEval (JavaScript)
|
| 62 |
-
metrics:
|
| 63 |
-
- name: pass@1
|
| 64 |
-
type: pass@1
|
| 65 |
-
value: 0.3079
|
| 66 |
-
verified: false
|
| 67 |
-
- task:
|
| 68 |
-
type: text-generation
|
| 69 |
-
dataset:
|
| 70 |
-
type: nuprl/MultiPL-E
|
| 71 |
-
name: MultiPL-HumanEval (Lua)
|
| 72 |
-
metrics:
|
| 73 |
-
- name: pass@1
|
| 74 |
-
type: pass@1
|
| 75 |
-
value: 0.2389
|
| 76 |
-
verified: false
|
| 77 |
-
- task:
|
| 78 |
-
type: text-generation
|
| 79 |
-
dataset:
|
| 80 |
-
type: nuprl/MultiPL-E
|
| 81 |
-
name: MultiPL-HumanEval (PHP)
|
| 82 |
-
metrics:
|
| 83 |
-
- name: pass@1
|
| 84 |
-
type: pass@1
|
| 85 |
-
value: 0.2608
|
| 86 |
-
verified: false
|
| 87 |
-
- task:
|
| 88 |
-
type: text-generation
|
| 89 |
-
dataset:
|
| 90 |
-
type: nuprl/MultiPL-E
|
| 91 |
-
name: MultiPL-HumanEval (Perl)
|
| 92 |
-
metrics:
|
| 93 |
-
- name: pass@1
|
| 94 |
-
type: pass@1
|
| 95 |
-
value: 0.1734
|
| 96 |
-
verified: false
|
| 97 |
-
- task:
|
| 98 |
-
type: text-generation
|
| 99 |
-
dataset:
|
| 100 |
-
type: nuprl/MultiPL-E
|
| 101 |
-
name: MultiPL-HumanEval (Python)
|
| 102 |
-
metrics:
|
| 103 |
-
- name: pass@1
|
| 104 |
-
type: pass@1
|
| 105 |
-
value: 0.3357
|
| 106 |
-
verified: false
|
| 107 |
-
- task:
|
| 108 |
-
type: text-generation
|
| 109 |
-
dataset:
|
| 110 |
-
type: nuprl/MultiPL-E
|
| 111 |
name: MultiPL-HumanEval (R)
|
| 112 |
metrics:
|
| 113 |
- name: pass@1
|
|
|
|
| 1 |
+
type: nuprl/MultiPL-E
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
name: MultiPL-HumanEval (R)
|
| 3 |
metrics:
|
| 4 |
- name: pass@1
|