Update README.md
Browse files
README.md
CHANGED
|
@@ -9,10 +9,10 @@ model-index:
|
|
| 9 |
results:
|
| 10 |
- task:
|
| 11 |
type: multiple-choice
|
| 12 |
-
name:
|
| 13 |
dataset:
|
| 14 |
type: Idavidrein/gpqa
|
| 15 |
-
name:
|
| 16 |
metrics:
|
| 17 |
- type: accuracy
|
| 18 |
value: 87.8
|
|
@@ -27,10 +27,10 @@ model-index:
|
|
| 27 |
value: 48.2
|
| 28 |
- task:
|
| 29 |
type: multiple-choice
|
| 30 |
-
name:
|
| 31 |
dataset:
|
| 32 |
type: TIGER-Lab/MMLU-Pro
|
| 33 |
-
name:
|
| 34 |
metrics:
|
| 35 |
- type: accuracy
|
| 36 |
value: 86.2
|
|
@@ -45,25 +45,25 @@ model-index:
|
|
| 45 |
value: 53.5
|
| 46 |
- task:
|
| 47 |
type: code-generation
|
| 48 |
-
name:
|
| 49 |
dataset:
|
| 50 |
type: SWE-bench/SWE-bench_Verified
|
| 51 |
-
name:
|
| 52 |
metrics:
|
| 53 |
- type: resolved
|
| 54 |
value: 77.2
|
| 55 |
- task:
|
| 56 |
type: multiple-choice
|
| 57 |
-
name:
|
| 58 |
dataset:
|
| 59 |
type: MMMU/MMMU_Pro
|
| 60 |
-
name:
|
| 61 |
metrics:
|
| 62 |
- type: accuracy
|
| 63 |
value: 75.8
|
| 64 |
- task:
|
| 65 |
type: multiple-choice
|
| 66 |
-
name: MathArena
|
| 67 |
dataset:
|
| 68 |
type: MathArena/aime_2026
|
| 69 |
name: default
|
|
@@ -81,7 +81,7 @@ model-index:
|
|
| 81 |
value: 59.3
|
| 82 |
- task:
|
| 83 |
type: text-generation
|
| 84 |
-
name:
|
| 85 |
dataset:
|
| 86 |
type: cais/hle
|
| 87 |
name: default
|
|
|
|
| 9 |
results:
|
| 10 |
- task:
|
| 11 |
type: multiple-choice
|
| 12 |
+
name: Diamond
|
| 13 |
dataset:
|
| 14 |
type: Idavidrein/gpqa
|
| 15 |
+
name: diamond # কনফিগ নেম diamond বসানো হয়েছে
|
| 16 |
metrics:
|
| 17 |
- type: accuracy
|
| 18 |
value: 87.8
|
|
|
|
| 27 |
value: 48.2
|
| 28 |
- task:
|
| 29 |
type: multiple-choice
|
| 30 |
+
name: Mmlu Pro
|
| 31 |
dataset:
|
| 32 |
type: TIGER-Lab/MMLU-Pro
|
| 33 |
+
name: pro # কনফিগ নেম pro বসানো হয়েছে
|
| 34 |
metrics:
|
| 35 |
- type: accuracy
|
| 36 |
value: 86.2
|
|
|
|
| 45 |
value: 53.5
|
| 46 |
- task:
|
| 47 |
type: code-generation
|
| 48 |
+
name: Swe Bench Resolved
|
| 49 |
dataset:
|
| 50 |
type: SWE-bench/SWE-bench_Verified
|
| 51 |
+
name: verified # কনফিগ নেম verified বসানো হয়েছে
|
| 52 |
metrics:
|
| 53 |
- type: resolved
|
| 54 |
value: 77.2
|
| 55 |
- task:
|
| 56 |
type: multiple-choice
|
| 57 |
+
name: Mmmu Pro Vision
|
| 58 |
dataset:
|
| 59 |
type: MMMU/MMMU_Pro
|
| 60 |
+
name: pro # কনফিগ নেম pro বসানো হয়েছে
|
| 61 |
metrics:
|
| 62 |
- type: accuracy
|
| 63 |
value: 75.8
|
| 64 |
- task:
|
| 65 |
type: multiple-choice
|
| 66 |
+
name: MathArena Aime 2026
|
| 67 |
dataset:
|
| 68 |
type: MathArena/aime_2026
|
| 69 |
name: default
|
|
|
|
| 81 |
value: 59.3
|
| 82 |
- task:
|
| 83 |
type: text-generation
|
| 84 |
+
name: Hle
|
| 85 |
dataset:
|
| 86 |
type: cais/hle
|
| 87 |
name: default
|