Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,43 @@ model-index:
|
|
| 10 |
name: MMLU
|
| 11 |
metrics:
|
| 12 |
- type: 5-shot
|
| 13 |
-
value:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
verified: false
|
| 15 |
---
|
| 16 |
|
|
|
|
| 10 |
name: MMLU
|
| 11 |
metrics:
|
| 12 |
- type: 5-shot
|
| 13 |
+
value: 58.90
|
| 14 |
+
verified: false
|
| 15 |
+
- task:
|
| 16 |
+
type: text-generation
|
| 17 |
+
dataset:
|
| 18 |
+
type: GPQA
|
| 19 |
+
name: GPQA
|
| 20 |
+
metrics:
|
| 21 |
+
- type: 0-shot
|
| 22 |
+
value: 29.91
|
| 23 |
+
verified: false
|
| 24 |
+
- task:
|
| 25 |
+
type: text-generation
|
| 26 |
+
dataset:
|
| 27 |
+
type: GSM-8K
|
| 28 |
+
name: GSM-8K
|
| 29 |
+
metrics:
|
| 30 |
+
- type: 8-shot, CoT
|
| 31 |
+
value: 34.12
|
| 32 |
+
verified: false
|
| 33 |
+
- task:
|
| 34 |
+
type: text-generation
|
| 35 |
+
dataset:
|
| 36 |
+
type: MATH
|
| 37 |
+
name: MATH
|
| 38 |
+
metrics:
|
| 39 |
+
- type: 4-shot, CoT
|
| 40 |
+
value: 8.36
|
| 41 |
+
verified: false
|
| 42 |
+
- task:
|
| 43 |
+
type: text-generation
|
| 44 |
+
dataset:
|
| 45 |
+
type: MT-bench
|
| 46 |
+
name: MT-bench
|
| 47 |
+
metrics:
|
| 48 |
+
- type: GPT4 Judge
|
| 49 |
+
value: 8.36
|
| 50 |
verified: false
|
| 51 |
---
|
| 52 |
|