Update README.md
Browse files
README.md
CHANGED
|
@@ -5,20 +5,29 @@ tags:
|
|
| 5 |
- model
|
| 6 |
- leaderboard
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results:
|
| 10 |
- task:
|
| 11 |
-
type: multiple-choice
|
| 12 |
-
name: GPQA
|
| 13 |
dataset:
|
| 14 |
type: Idavidrein/gpqa
|
| 15 |
-
name: default
|
| 16 |
metrics:
|
| 17 |
-
- type: accuracy
|
| 18 |
value: 87.8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
- task:
|
| 20 |
type: multiple-choice
|
| 21 |
-
name: MMLU
|
| 22 |
dataset:
|
| 23 |
type: TIGER-Lab/MMLU-Pro
|
| 24 |
name: default
|
|
@@ -26,14 +35,32 @@ model-index:
|
|
| 26 |
- type: accuracy
|
| 27 |
value: 86.2
|
| 28 |
- task:
|
| 29 |
-
type:
|
| 30 |
name: SWE Bench Pro
|
| 31 |
dataset:
|
| 32 |
type: ScaleAI/SWE-bench_Pro
|
| 33 |
name: default
|
| 34 |
metrics:
|
| 35 |
-
- type:
|
| 36 |
value: 53.5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
- task:
|
| 38 |
type: multiple-choice
|
| 39 |
name: MathArena AIME 2026
|
|
@@ -43,4 +70,31 @@ model-index:
|
|
| 43 |
metrics:
|
| 44 |
- type: accuracy
|
| 45 |
value: 94.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
---
|
|
|
|
| 5 |
- model
|
| 6 |
- leaderboard
|
| 7 |
model-index:
|
| 8 |
+
- name: droplychee/DropLychee-1.2
|
| 9 |
results:
|
| 10 |
- task:
|
| 11 |
+
type: multiple-choice
|
| 12 |
+
name: GPQA Diamond
|
| 13 |
dataset:
|
| 14 |
type: Idavidrein/gpqa
|
| 15 |
+
name: default
|
| 16 |
metrics:
|
| 17 |
+
- type: accuracy
|
| 18 |
value: 87.8
|
| 19 |
+
- task:
|
| 20 |
+
type: text-generation
|
| 21 |
+
name: SkillsBench V1.1
|
| 22 |
+
dataset:
|
| 23 |
+
type: benchflow/skillsbench
|
| 24 |
+
name: default
|
| 25 |
+
metrics:
|
| 26 |
+
- type: accuracy
|
| 27 |
+
value: 48.2
|
| 28 |
- task:
|
| 29 |
type: multiple-choice
|
| 30 |
+
name: MMLU Pro
|
| 31 |
dataset:
|
| 32 |
type: TIGER-Lab/MMLU-Pro
|
| 33 |
name: default
|
|
|
|
| 35 |
- type: accuracy
|
| 36 |
value: 86.2
|
| 37 |
- task:
|
| 38 |
+
type: code-generation
|
| 39 |
name: SWE Bench Pro
|
| 40 |
dataset:
|
| 41 |
type: ScaleAI/SWE-bench_Pro
|
| 42 |
name: default
|
| 43 |
metrics:
|
| 44 |
+
- type: pass@1
|
| 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: default
|
| 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: default
|
| 61 |
+
metrics:
|
| 62 |
+
- type: accuracy
|
| 63 |
+
value: 75.8
|
| 64 |
- task:
|
| 65 |
type: multiple-choice
|
| 66 |
name: MathArena AIME 2026
|
|
|
|
| 70 |
metrics:
|
| 71 |
- type: accuracy
|
| 72 |
value: 94.1
|
| 73 |
+
- task:
|
| 74 |
+
type: text-generation
|
| 75 |
+
name: Terminalbench 2
|
| 76 |
+
dataset:
|
| 77 |
+
type: harborframework/terminal-bench-2.0
|
| 78 |
+
name: default
|
| 79 |
+
metrics:
|
| 80 |
+
- type: accuracy
|
| 81 |
+
value: 59.3
|
| 82 |
+
- task:
|
| 83 |
+
type: text-generation
|
| 84 |
+
name: HLE
|
| 85 |
+
dataset:
|
| 86 |
+
type: cais/hle
|
| 87 |
+
name: default
|
| 88 |
+
metrics:
|
| 89 |
+
- type: accuracy
|
| 90 |
+
value: 24.0
|
| 91 |
+
- task:
|
| 92 |
+
type: multiple-choice
|
| 93 |
+
name: MathArena Hmmt Feb 2026
|
| 94 |
+
dataset:
|
| 95 |
+
type: MathArena/hmmt_feb_2026
|
| 96 |
+
name: default
|
| 97 |
+
metrics:
|
| 98 |
+
- type: accuracy
|
| 99 |
+
value: 84.3
|
| 100 |
---
|