Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ model-index:
|
|
| 24 |
type: MATH500
|
| 25 |
metrics:
|
| 26 |
- type: pass@1
|
| 27 |
-
value: 0.
|
| 28 |
name: pass@1
|
| 29 |
verified: false
|
| 30 |
- task:
|
|
@@ -34,7 +34,7 @@ model-index:
|
|
| 34 |
type: AMC23
|
| 35 |
metrics:
|
| 36 |
- type: pass@1
|
| 37 |
-
value: 0.
|
| 38 |
name: pass@1
|
| 39 |
verified: false
|
| 40 |
- task:
|
|
@@ -44,7 +44,7 @@ model-index:
|
|
| 44 |
type: OlympiadBench
|
| 45 |
metrics:
|
| 46 |
- type: pass@1
|
| 47 |
-
value: 0.
|
| 48 |
name: pass@1
|
| 49 |
verified: false
|
| 50 |
- task:
|
|
@@ -54,7 +54,7 @@ model-index:
|
|
| 54 |
type: MinervaMath
|
| 55 |
metrics:
|
| 56 |
- type: pass@1
|
| 57 |
-
value: 0.
|
| 58 |
name: pass@1
|
| 59 |
verified: false
|
| 60 |
- task:
|
|
@@ -64,11 +64,17 @@ model-index:
|
|
| 64 |
type: AIME24
|
| 65 |
metrics:
|
| 66 |
- type: pass@1
|
| 67 |
-
value: 0.
|
| 68 |
name: pass@1
|
| 69 |
verified: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
- type: pass@1
|
| 71 |
-
value: 0.
|
| 72 |
name: pass@1
|
| 73 |
verified: false
|
| 74 |
---
|
|
|
|
| 24 |
type: MATH500
|
| 25 |
metrics:
|
| 26 |
- type: pass@1
|
| 27 |
+
value: 0.869
|
| 28 |
name: pass@1
|
| 29 |
verified: false
|
| 30 |
- task:
|
|
|
|
| 34 |
type: AMC23
|
| 35 |
metrics:
|
| 36 |
- type: pass@1
|
| 37 |
+
value: 0.747
|
| 38 |
name: pass@1
|
| 39 |
verified: false
|
| 40 |
- task:
|
|
|
|
| 44 |
type: OlympiadBench
|
| 45 |
metrics:
|
| 46 |
- type: pass@1
|
| 47 |
+
value: 0.523
|
| 48 |
name: pass@1
|
| 49 |
verified: false
|
| 50 |
- task:
|
|
|
|
| 54 |
type: MinervaMath
|
| 55 |
metrics:
|
| 56 |
- type: pass@1
|
| 57 |
+
value: 0.495
|
| 58 |
name: pass@1
|
| 59 |
verified: false
|
| 60 |
- task:
|
|
|
|
| 64 |
type: AIME24
|
| 65 |
metrics:
|
| 66 |
- type: pass@1
|
| 67 |
+
value: 0.342
|
| 68 |
name: pass@1
|
| 69 |
verified: false
|
| 70 |
+
- task:
|
| 71 |
+
type: text-generation
|
| 72 |
+
dataset:
|
| 73 |
+
name: AIME25
|
| 74 |
+
type: AIME25
|
| 75 |
+
metrics:
|
| 76 |
- type: pass@1
|
| 77 |
+
value: 0.235
|
| 78 |
name: pass@1
|
| 79 |
verified: false
|
| 80 |
---
|