Spaces:
Running
Running
Update space
Browse files- src/populate.py +1 -1
src/populate.py
CHANGED
|
@@ -30,7 +30,7 @@ LEADERBOARD_DATA = [
|
|
| 30 |
{"model": "GPT-5-2025-08-07", "link": None, "Avg": 67.55, "Nar": 69.44, "MT": 66.67, "Con": 66.20, "IF": 82.00, "Scn": 65.91, "Saf": 60.17, "Att": 62.50},
|
| 31 |
{"model": "Claude-3-7-sonnet-20250219", "link": None, "Avg": 65.24, "Nar": 68.52, "MT": 62.70, "Con": 65.49, "IF": 75.00, "Scn": 62.88, "Saf": 61.02, "Att": 61.76},
|
| 32 |
# Ours
|
| 33 |
-
{"model": "RoleRM", "link": None, "Avg": 88.32, "Nar": 90.74, "MT": 82.54, "Con": 80.28, "IF": 94.00, "Scn": 90.91, "Saf": 91.53, "Att": 88.24},
|
| 34 |
]
|
| 35 |
|
| 36 |
|
|
|
|
| 30 |
{"model": "GPT-5-2025-08-07", "link": None, "Avg": 67.55, "Nar": 69.44, "MT": 66.67, "Con": 66.20, "IF": 82.00, "Scn": 65.91, "Saf": 60.17, "Att": 62.50},
|
| 31 |
{"model": "Claude-3-7-sonnet-20250219", "link": None, "Avg": 65.24, "Nar": 68.52, "MT": 62.70, "Con": 65.49, "IF": 75.00, "Scn": 62.88, "Saf": 61.02, "Att": 61.76},
|
| 32 |
# Ours
|
| 33 |
+
{"model": "Youtu-RoleRM", "link": None, "Avg": 88.32, "Nar": 90.74, "MT": 82.54, "Con": 80.28, "IF": 94.00, "Scn": 90.91, "Saf": 91.53, "Att": 88.24},
|
| 34 |
]
|
| 35 |
|
| 36 |
|