Update app.py
Browse files
app.py
CHANGED
|
@@ -34,7 +34,10 @@ head_style = """
|
|
| 34 |
DATA_URL_BASE = "http://opencompass.oss-cn-shanghai.aliyuncs.com/dev-assets/hf-research/"
|
| 35 |
|
| 36 |
MAIN_LEADERBOARD_DESCRIPTION = """## Compass Academic Leaderboard (Full Version)
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
"""
|
| 40 |
Initial_title = 'Compass Academic Leaderboard'
|
|
|
|
| 34 |
DATA_URL_BASE = "http://opencompass.oss-cn-shanghai.aliyuncs.com/dev-assets/hf-research/"
|
| 35 |
|
| 36 |
MAIN_LEADERBOARD_DESCRIPTION = """## Compass Academic Leaderboard (Full Version)
|
| 37 |
+
The CompassAcademic currently focuses on the comprehensive reasoning abilities of LLMs.
|
| 38 |
+
- The datasets selected so far include General Knowledge Reasoning (MMLU-Pro/GPQA-Diamond), Logical Reasoning (BBH), Mathematical Reasoning (MATH-500, AIME), Code Completion (LiveCodeBench, HumanEval), and Instruction Following (IFEval).
|
| 39 |
+
- Currently, the evaluation primarily targets chat models, with updates featuring the latest community models at irregular intervals.
|
| 40 |
+
- Prompts and reproduction scripts can be found in [**OpenCompass**: A Toolkit for Evaluation of LLMs](https://github.com/open-compass/opencompass)🏆.
|
| 41 |
|
| 42 |
"""
|
| 43 |
Initial_title = 'Compass Academic Leaderboard'
|