Commit
·
23b60ae
1
Parent(s):
96dd699
make it clcikabnle
Browse files- app.py +1 -1
- human_Mind2Web-Online - Leaderboard_data.csv +1 -1
app.py
CHANGED
|
@@ -45,7 +45,7 @@ def get_dataframe_from_results(eval_path):
|
|
| 45 |
|
| 46 |
auto_eval_dataframe_test = get_dataframe_from_results('./auto_o4-mini_Mind2Web-Online - Leaderboard_data.csv')
|
| 47 |
human_eval_dataframe_test = get_dataframe_from_results('./human_Mind2Web-Online - Leaderboard_data.csv')
|
| 48 |
-
TYPES = ["
|
| 49 |
|
| 50 |
def df_to_gradio(df: pd.DataFrame) -> dict:
|
| 51 |
display_df = df.drop(columns=["Release Time"], errors="ignore")
|
|
|
|
| 45 |
|
| 46 |
auto_eval_dataframe_test = get_dataframe_from_results('./auto_o4-mini_Mind2Web-Online - Leaderboard_data.csv')
|
| 47 |
human_eval_dataframe_test = get_dataframe_from_results('./human_Mind2Web-Online - Leaderboard_data.csv')
|
| 48 |
+
TYPES = ["markdown", "str", "markdown", "markdown", "number", "number", "number", "number", "str", "str", "markdown", "str"]
|
| 49 |
|
| 50 |
def df_to_gradio(df: pd.DataFrame) -> dict:
|
| 51 |
display_df = df.drop(columns=["Release Time"], errors="ignore")
|
human_Mind2Web-Online - Leaderboard_data.csv
CHANGED
|
@@ -8,4 +8,4 @@ Claude Computer Use 3.7 (w/o thinking),Claude-3-7-sonnet-20250219,Anthropic,OSU
|
|
| 8 |
ACT-1-20250703,o3-2025-04-16 and Claude-sonnet-4-20250514,Enhans,Enhans,65.1,46.2,23.0,45.7,2025-7-16
|
| 9 |
ACT-1-20250814,o3-2025-04-16 and Claude-sonnet-4-20250514,Enhans,Enhans,81.9,54.5,35.1,57.3,2025-8-23
|
| 10 |
Google Computer Use (09-2025),Gemini 2.5 Computer Use,Google DeepMind,Google DeepMind,77.1,71.3,55.4,69.0,2025-9-29
|
| 11 |
-
Navigator,n1-preview-11-2025,Yutori,[Halluminate](https://halluminate.ai/),90.1,76.2,71.1,78.7,2025-11-18
|
|
|
|
| 8 |
ACT-1-20250703,o3-2025-04-16 and Claude-sonnet-4-20250514,Enhans,Enhans,65.1,46.2,23.0,45.7,2025-7-16
|
| 9 |
ACT-1-20250814,o3-2025-04-16 and Claude-sonnet-4-20250514,Enhans,Enhans,81.9,54.5,35.1,57.3,2025-8-23
|
| 10 |
Google Computer Use (09-2025),Gemini 2.5 Computer Use,Google DeepMind,Google DeepMind,77.1,71.3,55.4,69.0,2025-9-29
|
| 11 |
+
[Navigator](https://yutori.com/blog/introducing-navigator),n1-preview-11-2025,[Yutori](https://yutori.com),[Halluminate](https://halluminate.ai/),90.1,76.2,71.1,78.7,2025-11-18
|