first commit

RESULTS.json

@@ -0,0 +1,686 @@
+{
+    "gpt-4o-2024-05-13": {
+        "readability": {
+            "R*": 80.5,
+            "RN_p": 81.1,
+            "RN_if": 91.8,
+            "RN": 75.3,
+            "RL_p": 78.9,
+            "RL_if": 78.9,
+            "RL": 63.2,
+            "RC_p": 79.8,
+            "RC_if": 78.7,
+            "RC": 64.3,
+            "MBPP*": 64.6,
+            "Readability": 67.6
+        },
+        "maintainability": {
+            "MI*": 38.0,
+            "MI_p": 35.0,
+            "MI": 75.1,
+            "MC*": 57.2,
+            "MC_p": 56.3,
+            "MC": 35.2,
+            "Maintainability": 55.1
+        },
+        "efficiency": {
+            "E*": 59.4,
+            "E_p": 58.4,
+            "E_NI_T": 44.8,
+            "E_NI_S": 42.0,
+            "Efficiency": 43.4
+        },
+        "correctness": {
+            "Correctness": 59.9
+        },
+        "overall": {
+            "RACE Score": 56.5
+        }
+    },
+    "gpt-3.5-turbo-0125": {
+        "readability": {
+            "R*": 62.8,
+            "RN_p": 63.2,
+            "RN_if": 74.4,
+            "RN": 48.3,
+            "RL_p": 60.4,
+            "RL_if": 76.8,
+            "RL": 46.1,
+            "RC_p": 65.8,
+            "RC_if": 60.0,
+            "RC": 41.5,
+            "MBPP*": 62.2,
+            "Readability": 45.3
+        },
+        "maintainability": {
+            "MI*": 28.0,
+            "MI_p": 24.0,
+            "MI": 80.2,
+            "MC*": 31.1,
+            "MC_p": 28.1,
+            "MC": 18.5,
+            "Maintainability": 49.4
+        },
+        "efficiency": {
+            "E*": 39.6,
+            "E_p": 32.7,
+            "E_NI_T": 27.5,
+            "E_NI_S": 36.5,
+            "Efficiency": 32.0
+        },
+        "correctness": {
+            "Correctness": 44.7
+        },
+        "overall": {
+            "RACE Score": 42.8
+        }
+    },
+    "CodeLlama-7b-Instruct-hf": {
+        "readability": {
+            "R*": 32.3,
+            "RN_p": 31.5,
+            "RN_if": 55.5,
+            "RN": 17.0,
+            "RL_p": 31.7,
+            "RL_if": 59.7,
+            "RL": 23.4,
+            "RC_p": 30.2,
+            "RC_if": 67.4,
+            "RC": 18.3,
+            "MBPP*": 43.1,
+            "Readability": 19.6
+        },
+        "maintainability": {
+            "MI*": 16.0,
+            "MI_p": 15.0,
+            "MI": 71.8,
+            "MC*": 12.2,
+            "MC_p": 10.9,
+            "MC": 7.2,
+            "Maintainability": 39.5
+        },
+        "efficiency": {
+            "E*": 15.8,
+            "E_p": 13.9,
+            "E_NI_T": 8.2,
+            "E_NI_S": 8.8,
+            "Efficiency": 8.5
+        },
+        "correctness": {
+            "Correctness": 23.9
+        },
+        "overall": {
+            "RACE Score": 22.9
+        }
+    },
+    "CodeLlama-7b-Python-hf": {
+        "readability": {
+            "R*": 29.3,
+            "RN_p": 29.5,
+            "RN_if": 66.4,
+            "RN": 20.4,
+            "RL_p": 30.1,
+            "RL_if": 76.6,
+            "RL": 25.8,
+            "RC_p": 24.7,
+            "RC_if": 42.1,
+            "RC": 11.6,
+            "MBPP*": 41.3,
+            "Readability": 19.3
+        },
+        "maintainability": {
+            "MI*": 11.0,
+            "MI_p": 10.0,
+            "MI": 79.4,
+            "MC*": 5.6,
+            "MC_p": 6.5,
+            "MC": 3.7,
+            "Maintainability": 41.6
+        },
+        "efficiency": {
+            "E*": 14.9,
+            "E_p": 15.8,
+            "E_NI_T": 14.3,
+            "E_NI_S": 14.4,
+            "Efficiency": 14.4
+        },
+        "correctness": {
+            "Correctness": 20.4
+        },
+        "overall": {
+            "RACE Score": 23.9
+        }
+    },
+    "CodeLlama-13b-Instruct-hf": {
+        "readability": {
+            "R*": 36.0,
+            "RN_p": 37.7,
+            "RN_if": 57.8,
+            "RN": 22.0,
+            "RL_p": 35.0,
+            "RL_if": 59.9,
+            "RL": 23.6,
+            "RC_p": 35.7,
+            "RC_if": 64.3,
+            "RC": 23.2,
+            "MBPP*": 40.7,
+            "Readability": 22.9
+        },
+        "maintainability": {
+            "MI*": 17.0,
+            "MI_p": 19.0,
+            "MI": 82.1,
+            "MC*": 10.6,
+            "MC_p": 13.1,
+            "MC": 7.6,
+            "Maintainability": 44.8
+        },
+        "efficiency": {
+            "E*": 17.8,
+            "E_p": 17.8,
+            "E_NI_T": 10.4,
+            "E_NI_S": 16.1,
+            "Efficiency": 13.2
+        },
+        "correctness": {
+            "Correctness": 24.4
+        },
+        "overall": {
+            "RACE Score": 26.4
+        }
+    },
+    "CodeLlama-13b-Python-hf": {
+        "readability": {
+            "R*": 40.2,
+            "RN_p": 35.0,
+            "RN_if": 61.3,
+            "RN": 22.4,
+            "RL_p": 34.8,
+            "RL_if": 83.5,
+            "RL": 30.9,
+            "RC_p": 30.2,
+            "RC_if": 60.7,
+            "RC": 20.4,
+            "MBPP*": 29.4,
+            "Readability": 24.6
+        },
+        "maintainability": {
+            "MI*": 16.0,
+            "MI_p": 15.0,
+            "MI": 78.6,
+            "MC*": 6.1,
+            "MC_p": 4.8,
+            "MC": 2.4,
+            "Maintainability": 40.5
+        },
+        "efficiency": {
+            "E*": 16.8,
+            "E_p": 17.8,
+            "E_NI_T": 13.8,
+            "E_NI_S": 14.7,
+            "Efficiency": 14.2
+        },
+        "correctness": {
+            "Correctness": 21.7
+        },
+        "overall": {
+            "RACE Score": 25.3
+        }
+    },
+    "CodeLlama-34b-Instruct-hf": {
+        "readability": {
+            "R*": 36.0,
+            "RN_p": 36.5,
+            "RN_if": 54.3,
+            "RN": 21.1,
+            "RL_p": 35.8,
+            "RL_if": 41.7,
+            "RL": 17.5,
+            "RC_p": 36.3,
+            "RC_if": 32.0,
+            "RC": 9.4,
+            "MBPP*": 45.8,
+            "Readability": 16.0
+        },
+        "maintainability": {
+            "MI*": 12.0,
+            "MI_p": 18.0,
+            "MI": 73.2,
+            "MC*": 15.6,
+            "MC_p": 14.2,
+            "MC": 8.5,
+            "Maintainability": 40.9
+        },
+        "efficiency": {
+            "E*": 20.8,
+            "E_p": 15.8,
+            "E_NI_T": 14.4,
+            "E_NI_S": 13.8,
+            "Efficiency": 14.1
+        },
+        "correctness": {
+            "Correctness": 26.0
+        },
+        "overall": {
+            "RACE Score": 24.2
+        }
+    },
+    "CodeLlama-34b-Python-hf": {
+        "readability": {
+            "R*": 31.7,
+            "RN_p": 27.2,
+            "RN_if": 66.9,
+            "RN": 18.6,
+            "RL_p": 32.5,
+            "RL_if": 73.2,
+            "RL": 26.7,
+            "RC_p": 27.8,
+            "RC_if": 39.4,
+            "RC": 6.7,
+            "MBPP*": 36.2,
+            "Readability": 17.3
+        },
+        "maintainability": {
+            "MI*": 3.0,
+            "MI_p": 2.0,
+            "MI": 85.3,
+            "MC*": 7.2,
+            "MC_p": 5.4,
+            "MC": 2.2,
+            "Maintainability": 43.8
+        },
+        "efficiency": {
+            "E*": 17.8,
+            "E_p": 11.9,
+            "E_NI_T": 12.0,
+            "E_NI_S": 14.4,
+            "Efficiency": 13.2
+        },
+        "correctness": {
+            "Correctness": 19.2
+        },
+        "overall": {
+            "RACE Score": 23.4
+        }
+    },
+    "deepseek-coder-6.7b-instruct": {
+        "readability": {
+            "R*": 65.2,
+            "RN_p": 65.5,
+            "RN_if": 67.2,
+            "RN": 44.4,
+            "RL_p": 61.2,
+            "RL_if": 73.6,
+            "RL": 46.6,
+            "RC_p": 61.2,
+            "RC_if": 65.5,
+            "RC": 42.0,
+            "MBPP*": 57.1,
+            "Readability": 44.3
+        },
+        "maintainability": {
+            "MI*": 26.0,
+            "MI_p": 25.0,
+            "MI": 79.3,
+            "MC*": 18.9,
+            "MC_p": 18.7,
+            "MC": 8.2,
+            "Maintainability": 43.8
+        },
+        "efficiency": {
+            "E*": 28.7,
+            "E_p": 30.7,
+            "E_NI_T": 27.1,
+            "E_NI_S": 30.0,
+            "Efficiency": 28.6
+        },
+        "correctness": {
+            "Correctness": 39.2
+        },
+        "overall": {
+            "RACE Score": 39.0
+        }
+    },
+    "deepseek-coder-7b-instruct-v1.5": {
+        "readability": {
+            "R*": 61.0,
+            "RN_p": 61.5,
+            "RN_if": 57.8,
+            "RN": 35.2,
+            "RL_p": 62.6,
+            "RL_if": 70.9,
+            "RL": 46.0,
+            "RC_p": 62.8,
+            "RC_if": 70.2,
+            "RC": 46.0,
+            "MBPP*": 59.3,
+            "Readability": 42.4
+        },
+        "maintainability": {
+            "MI*": 23.0,
+            "MI_p": 24.0,
+            "MI": 79.6,
+            "MC*": 23.3,
+            "MC_p": 20.9,
+            "MC": 8.9,
+            "Maintainability": 44.2
+        },
+        "efficiency": {
+            "E*": 32.7,
+            "E_p": 27.7,
+            "E_NI_T": 25.1,
+            "E_NI_S": 26.8,
+            "Efficiency": 26.0
+        },
+        "correctness": {
+            "Correctness": 39.9
+        },
+        "overall": {
+            "RACE Score": 38.1
+        }
+    },
+    "deepseek-coder-33b-instruct": {
+        "readability": {
+            "R*": 65.9,
+            "RN_p": 64.6,
+            "RN_if": 86.8,
+            "RN": 57.7,
+            "RL_p": 65.0,
+            "RL_if": 82.7,
+            "RL": 53.5,
+            "RC_p": 66.5,
+            "RC_if": 70.8,
+            "RC": 46.4,
+            "MBPP*": 61.9,
+            "Readability": 52.5
+        },
+        "maintainability": {
+            "MI*": 28.0,
+            "MI_p": 30.0,
+            "MI": 75.7,
+            "MC*": 22.2,
+            "MC_p": 27.6,
+            "MC": 11.3,
+            "Maintainability": 43.5
+        },
+        "efficiency": {
+            "E*": 45.5,
+            "E_p": 38.6,
+            "E_NI_T": 35.3,
+            "E_NI_S": 36.1,
+            "Efficiency": 35.7
+        },
+        "correctness": {
+            "Correctness": 44.7
+        },
+        "overall": {
+            "RACE Score": 44.1
+        }
+    },
+    "DeepSeek-Coder-V2-Lite-Instruct": {
+        "readability": {
+            "R*": 72.0,
+            "RN_p": 71.2,
+            "RN_if": 55.3,
+            "RN": 40.2,
+            "RL_p": 66.5,
+            "RL_if": 83.7,
+            "RL": 57.7,
+            "RC_p": 67.1,
+            "RC_if": 63.5,
+            "RC": 42.7,
+            "MBPP*": 62.7,
+            "Readability": 46.9
+        },
+        "maintainability": {
+            "MI*": 26.0,
+            "MI_p": 30.0,
+            "MI": 78.2,
+            "MC*": 44.4,
+            "MC_p": 44.3,
+            "MC": 19.8,
+            "Maintainability": 49.0
+        },
+        "efficiency": {
+            "E*": 49.5,
+            "E_p": 55.4,
+            "E_NI_T": 40.2,
+            "E_NI_S": 47.7,
+            "Efficiency": 44.0
+        },
+        "correctness": {
+            "Correctness": 50.9
+        },
+        "overall": {
+            "RACE Score": 47.7
+        }
+    },
+    "deepseek-coder": {
+        "readability": {
+            "R*": 73.8,
+            "RN_p": 75.3,
+            "RN_if": 91.8,
+            "RN": 70.0,
+            "RL_p": 75.2,
+            "RL_if": 88.4,
+            "RL": 67.1,
+            "RC_p": 76.5,
+            "RC_if": 74.1,
+            "RC": 58.5,
+            "MBPP*": 68.5,
+            "Readability": 65.2
+        },
+        "maintainability": {
+            "MI*": 35.0,
+            "MI_p": 38.0,
+            "MI": 77.3,
+            "MC*": 58.9,
+            "MC_p": 58.9,
+            "MC": 35.0,
+            "Maintainability": 56.1
+        },
+        "efficiency": {
+            "E*": 57.3,
+            "E_p": 53.5,
+            "E_NI_T": 41.1,
+            "E_NI_S": 49.4,
+            "Efficiency": 45.2
+        },
+        "correctness": {
+            "Correctness": 58.7
+        },
+        "overall": {
+            "RACE Score": 56.3
+        }
+    },
+    "WizardCoder-Python-7B-V1.0": {
+        "readability": {
+            "R*": 34.8,
+            "RN_p": 35.8,
+            "RN_if": 58.3,
+            "RN": 22.4,
+            "RL_p": 34.3,
+            "RL_if": 79.7,
+            "RL": 28.0,
+            "RC_p": 35.4,
+            "RC_if": 25.0,
+            "RC": 8.6,
+            "MBPP*": 41.8,
+            "Readability": 19.7
+        },
+        "maintainability": {
+            "MI*": 19.0,
+            "MI_p": 23.0,
+            "MI": 79.3,
+            "MC*": 10.6,
+            "MC_p": 9.8,
+            "MC": 7.2,
+            "Maintainability": 43.2
+        },
+        "efficiency": {
+            "E*": 19.8,
+            "E_p": 19.8,
+            "E_NI_T": 15.3,
+            "E_NI_S": 16.7,
+            "Efficiency": 16.0
+        },
+        "correctness": {
+            "Correctness": 25.2
+        },
+        "overall": {
+            "RACE Score": 26.0
+        }
+    },
+    "WizardCoder-Python-13B-V1.0": {
+        "readability": {
+            "R*": 36.0,
+            "RN_p": 38.2,
+            "RN_if": 58.4,
+            "RN": 23.1,
+            "RL_p": 38.4,
+            "RL_if": 83.1,
+            "RL": 33.1,
+            "RC_p": 43.6,
+            "RC_if": 59.8,
+            "RC": 27.4,
+            "MBPP*": 42.1,
+            "Readability": 27.9
+        },
+        "maintainability": {
+            "MI*": 20.0,
+            "MI_p": 21.0,
+            "MI": 78.8,
+            "MC*": 12.8,
+            "MC_p": 12.8,
+            "MC": 8.5,
+            "Maintainability": 43.6
+        },
+        "efficiency": {
+            "E*": 20.8,
+            "E_p": 18.8,
+            "E_NI_T": 16.2,
+            "E_NI_S": 19.8,
+            "Efficiency": 18.0
+        },
+        "correctness": {
+            "Correctness": 26.3
+        },
+        "overall": {
+            "RACE Score": 29.0
+        }
+    },
+    "WizardCoder-15B-V1.0": {
+        "readability": {
+            "R*": 38.4,
+            "RN_p": 38.7,
+            "RN_if": 59.0,
+            "RN": 23.2,
+            "RL_p": 41.9,
+            "RL_if": 64.8,
+            "RL": 27.8,
+            "RC_p": 40.0,
+            "RC_if": 57.3,
+            "RC": 24.4,
+            "MBPP*": 46.3,
+            "Readability": 25.1
+        },
+        "maintainability": {
+            "MI*": 22.0,
+            "MI_p": 21.0,
+            "MI": 80.0,
+            "MC*": 11.7,
+            "MC_p": 11.5,
+            "MC": 7.8,
+            "Maintainability": 43.9
+        },
+        "efficiency": {
+            "E*": 21.8,
+            "E_p": 22.8,
+            "E_NI_T": 21.8,
+            "E_NI_S": 24.2,
+            "Efficiency": 23.0
+        },
+        "correctness": {
+            "Correctness": 28.0
+        },
+        "overall": {
+            "RACE Score": 30.0
+        }
+    },
+    "WizardCoder-33B-V1.1": {
+        "readability": {
+            "R*": 58.5,
+            "RN_p": 58.8,
+            "RN_if": 65.4,
+            "RN": 39.9,
+            "RL_p": 62.2,
+            "RL_if": 76.0,
+            "RL": 47.6,
+            "RC_p": 58.8,
+            "RC_if": 61.0,
+            "RC": 37.2,
+            "MBPP*": 64.6,
+            "Readability": 41.6
+        },
+        "maintainability": {
+            "MI*": 34.0,
+            "MI_p": 34.0,
+            "MI": 71.2,
+            "MC*": 26.1,
+            "MC_p": 25.0,
+            "MC": 9.3,
+            "Maintainability": 40.2
+        },
+        "efficiency": {
+            "E*": 38.6,
+            "E_p": 35.6,
+            "E_NI_T": 33.9,
+            "E_NI_S": 34.9,
+            "Efficiency": 34.4
+        },
+        "correctness": {
+            "Correctness": 44.4
+        },
+        "overall": {
+            "RACE Score": 40.1
+        }
+    },
+    "CodeQwen1.5-7B-Chat": {
+        "readability": {
+            "R*": 76.2,
+            "RN_p": 76.8,
+            "RN_if": 60.8,
+            "RN": 47.0,
+            "RL_p": 73.4,
+            "RL_if": 60.8,
+            "RL": 47.0,
+            "RC_p": 74.7,
+            "RC_if": 71.3,
+            "RC": 54.2,
+            "MBPP*": 60.3,
+            "Readability": 49.4
+        },
+        "maintainability": {
+            "MI*": 22.0,
+            "MI_p": 22.0,
+            "MI": 82.3,
+            "MC*": 33.3,
+            "MC_p": 32.6,
+            "MC": 13.0,
+            "Maintainability": 47.6
+        },
+        "efficiency": {
+            "E*": 39.6,
+            "E_p": 38.6,
+            "E_NI_T": 30.7,
+            "E_NI_S": 37.7,
+            "Efficiency": 34.2
+        },
+        "correctness": {
+            "Correctness": 46.3
+        },
+        "overall": {
+            "RACE Score": 44.4
+        }
+    }
+}

app.py

@@ -0,0 +1,144 @@
+import json
+
+import gradio as gr
+import pandas as pd
+
+from css_html import custom_css
+from text_content import ABOUT_TEXT, CITATION_BUTTON_TEXT, CITATION_BUTTON_LABEL, ACKNOWLEDGEMENT_TEXT, NOTES_TEXT
+from utils import (
+    AutoEvalColumn,
+    fields,
+)
+
+result_path = './RESULTS.json'
+with open(result_path, 'r') as f:
+    data = json.load(f)
+    
+    rows = []
+    for col, subcols in data.items():
+        row = {"model": col}
+        for subcol, datas in subcols.items():
+            if subcol == 'readability':
+                symbol = '📖'
+            elif subcol == 'maintainability':
+                symbol = '🔨'
+            elif subcol == 'efficiency':
+                symbol = '🚀'
+            elif subcol == 'correctness':
+                symbol = '✅'
+            elif subcol == 'overall':
+                symbol = '💯'
+                
+            for key, value in datas.items():
+                row[f'{symbol} {key}'] = value
+
+        rows.append(row)
+        
+    df = pd.DataFrame(rows)
+    df = df.sort_values(by='💯 RACE Score', ascending=False)
+
+COLS = [c.name for c in fields(AutoEvalColumn) if not c.hidden]
+TYPES = [c.type for c in fields(AutoEvalColumn) if not c.hidden]
+COLS_LITE = [
+    c.name for c in fields(AutoEvalColumn) if c.displayed_by_default and not c.hidden
+]
+TYPES_LITE = [
+    c.type for c in fields(AutoEvalColumn) if c.displayed_by_default and not c.hidden
+]
+
+def select_columns(df, columns):
+    always_here_cols = [
+        AutoEvalColumn.model.name,
+    ]
+    # We use COLS to maintain sorting
+    filtered_df = df[
+        always_here_cols + [c for c in COLS if c in df.columns and c in columns]
+    ]
+    return filtered_df
+
+demo = gr.Blocks(css=custom_css)
+with demo:
+    with gr.Row():
+        gr.Markdown(
+            """<div style="text-align: center;"><h1> 🏎️RACE Leaderboard</h1></div>\
+            <br>\
+            <p>Based on the 🏎️RACE benchmark, we demonstrated the ability of different LLMs to generate code that is <b><i>correct</i></b> and <b><i>meets the requirements of real-world development scenarios</i></b>.</p>
+            <p>Model details about how to evalute the LLM are available in the <a href="https://github.com/test/test">🏎️RACE GitHub repository</a>.</p>
+""",
+            elem_classes="markdown-text",
+        )
+
+    with gr.Tabs(elem_classes="tab-buttons") as tabs:
+        with gr.Column():
+            with gr.Tabs(elem_classes="A100-tabs") as A100_tabs:
+                with gr.TabItem("🔍 Evaluation Table", id=0):
+                    with gr.Column():
+                        with gr.Accordion("⏬ Hidden Columns", open=False):
+                            shown_columns = gr.CheckboxGroup(
+                                choices=[
+                                    c
+                                    for c in COLS
+                                    if c
+                                    not in [
+                                        AutoEvalColumn.model.name,
+                                    ]
+                                ],
+                                value=[
+                                    c
+                                    for c in COLS_LITE
+                                    if c
+                                    not in [
+                                        AutoEvalColumn.model.name,
+                                    ]
+                                ],
+                                label="",
+                                elem_id="column-select",
+                                interactive=True,
+                            )
+                            
+                    leaderboard_df = gr.components.Dataframe(
+                        value=df[
+                            [
+                                AutoEvalColumn.model.name,
+                            ]
+                            + shown_columns.value
+                        ],
+                        headers=COLS,
+                        datatype=TYPES,
+                        elem_id="leaderboard-table",
+                        interactive=False,
+                    )
+
+                    hidden_leaderboard_df = gr.components.Dataframe(
+                        value=df,
+                        headers=COLS,
+                        datatype=["str" for _ in range(len(COLS))],
+                        visible=False,
+                    )
+                    
+                    shown_columns.change(
+                        select_columns,
+                        [hidden_leaderboard_df, shown_columns],
+                        leaderboard_df,
+                    )
+                    
+                    gr.Markdown(NOTES_TEXT, elem_classes="markdown-text")
+                        
+                with gr.TabItem("📝 About", id=1):
+                    gr.Markdown(ABOUT_TEXT, elem_classes="markdown-text")
+                    
+        with gr.Row():
+            with gr.Accordion("📙 Citation", open=False):
+                citation_button = gr.Textbox(
+                    value=CITATION_BUTTON_TEXT,
+                    label=CITATION_BUTTON_LABEL,
+                    lines=10,
+                    elem_id="citation-button",
+                    show_copy_button=True,
+                )
+        
+        with gr.Row():
+            with gr.Accordion("🙏 Acknowledgement", open=False):
+                gr.Markdown(ACKNOWLEDGEMENT_TEXT)
+
+demo.launch()

css_html.py

@@ -0,0 +1,64 @@
+custom_css = """
+#changelog-text {
+    font-size: 16px !important;
+}
+#changelog-text h2 {
+    font-size: 18px !important;
+}
+.markdown-text {
+    font-size: 16px !important;
+}
+#models-to-add-text {
+    font-size: 18px !important;
+}
+#citation-button span {
+    font-size: 16px !important;
+}
+#citation-button textarea {
+    font-size: 16px !important;
+}
+#citation-button > label > button {
+    margin: 6px;
+    transform: scale(1.3);
+}
+#leaderboard-table {
+    margin-top: 15px
+}
+#leaderboard-table-lite {
+    margin-top: 15px
+}
+#search-bar-table-box > div:first-child {
+    background: none;
+    border: none;
+}
+ 
+#search-bar {
+    padding: 0px;
+}
+/* Hides the final AutoEvalColumn */
+#llm-benchmark-tab-table table td:last-child,
+#llm-benchmark-tab-table table th:last-child {
+    display: none;
+}
+/* Limit the width of the first AutoEvalColumn so that names don't expand too much */
+table td:first-child,
+table th:first-child {
+    max-width: 400px;
+    overflow: auto;
+    white-space: nowrap;
+}
+.tab-buttons button {
+    font-size: 20px;
+}
+#scale-logo {
+    border-style: none !important;
+    box-shadow: none;
+    display: block;
+    margin-left: auto;
+    margin-right: auto;
+    max-width: 600px;
+}
+#scale-logo .download {
+    display: none;
+}
+"""

text_content.py

@@ -0,0 +1,63 @@
+ABOUT_TEXT = """# What is RACE benchmark?
+RACE is a multi-dimensional benchmark for code generation that focuses on **R**eadability, m**A**intainability, **C**orrectness, and **E**fficiency. 
+Its goal is to evaluate LLM's ability to generate code that is correct and meets the requirements of real-world development scenarios. 
+The benchmark is designed with various real-world demands across different **_demand-dependent_** dimensions, making it more applicable to practical scenarios. 
+
+# What are the specific aspects to be evaluated?
+We have summarized representative influencing factors in real-world scenarios for different dimensions and designed various requirements for each factor. 
+These have been incorporated into the task description to prompt the LLM to generate code that is correct and meets the specified requirements.
+The specific factors are as follows:
+- **Readability**: The code should be easy to read and understand.
+  - `Comment`
+  - `Naming Convention`
+  - `Code Length`
+- **Maintainability**: The code should be easy to maintain and extend.
+  - `MI Metric`
+  - `Modularity`
+- **Efficiency**: The code should be efficient in terms of time and space complexity.
+  - `Time Complexity`
+  - `Space Complexity`
+
+# How to evaluate?
+To facilitate evaluation on the RACE benchmark, we provide the evaluation data and easy-to-use evaluation scripts in our 🏎️RACE GitHub repository. 
+Additionally, factors involving execution-based evaluation are conducted in a virtual environment to ensure evaluation security.
+
+# Contact
+If you have any questions, feel free to reach out to us at [[email protected]](mailto:[email protected]).
+
+# Citation Information
+```bibtex
+
+```
+"""
+
+CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
+
+CITATION_BUTTON_TEXT = r"""
+
+"""
+
+ACKNOWLEDGEMENT_TEXT = """
+Inspired from the [🤗 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
+"""
+
+
+NOTES_TEXT = """
+**Notes:**
+- `💯 RACE Score` denotes the final evaluation result based on 🏎️RACE benchmark, which is the average of the scores in the four dimensions: `✅ Correctness`, `📖 Readability`, `🔨 Maintainability`, and `🚀 Efficiency`.
+- All fine-grained evaluation results are provided in `⏬ Hidden Columns`. `📖 R` denotes code **R**eadability, `🔨 M` denotes code **M**aintainability, and `🚀 E` denotes code **E**fficiency. `*` denotes the correctness of the code in the corresponding dimension. More details about the abbreviations are as follows:
+    - `📖 R*`: The code accuracy (baesline).
+    - `📖 RN`: The proportion of code that is both functionally correct and follows customized instructions related to `Naming Convention`.
+    - `📖 RL`: The proportion of code that is both functionally correct and follows customized instructions related to `Code Length`.
+    - `📖 RC`: The proportion of code that is both functionally correct and follows customized instructions related to `Comment`.
+    - `🔨 MI*`: The code accuracy related to `Maintainability Index` (baesline).
+    - `🔨 MI`: The proportion of code that is both functionally correct and follows customized instructions related to `MI Metric`.
+    - `🔨 MC*`: The code accuracy related to `Modularity` (baesline).
+    - `🔨 MC`: The proportion of code that is both functionally correct and follows customized instructions related to `Modularity`.
+    - `🚀 E*`:  The code accuracy (baesline).
+    - `🚀 E_NI_T`: The proportion of code that is both functionally correct and follows customized instructions related to `Time Complexity`.
+    - `🚀 E_NI_S`: The proportion of code that is both functionally correct and follows customized instructions related to `Space Complexity`.
+
+- Regarding the types of evaluation results, `🔨 MI`, `🚀 E_NI_T`, and `🚀 E_NI_S` are scalar values ranging from 0 to 100, while the remaining metrics are percentages.
+- For more explanation check the 📝 About section.
+"""

utils.py

@@ -0,0 +1,37 @@
+from dataclasses import dataclass
+
+
+@dataclass
+class ColumnContent:
+    name: str
+    type: str
+    displayed_by_default: bool
+    hidden: bool = False
+
+
+def fields(raw_class):
+    return [
+        v for k, v in raw_class.__dict__.items() if k[:2] != "__" and k[-2:] != "__"
+    ]
+
+
+@dataclass(frozen=True)
+class AutoEvalColumn:  # Auto evals column
+    model = ColumnContent("model", "markdown", True)
+    score = ColumnContent("💯 RACE Score", "number", True)
+    c_0 = ColumnContent("✅ Correctness", "number", True)
+    r_0 = ColumnContent("📖 Readability", "number", True)
+    r_1 = ColumnContent("📖 R*", "number", False)
+    r_2 = ColumnContent("📖 RN", "number", False)
+    r_3 = ColumnContent("📖 RL", "number", False)
+    r_4 = ColumnContent("📖 RC", "number", False)
+    m_0 = ColumnContent("🔨 Maintainability", "number", True)
+    m_1 = ColumnContent("🔨 MI*", "number", False)
+    m_2 = ColumnContent("🔨 MI", "number", False)
+    m_3 = ColumnContent("🔨 MC*", "number", False)
+    m_4 = ColumnContent("🔨 MC", "number", False)
+    e_0 = ColumnContent("🚀 Efficiency", "number", True)
+    e_1 = ColumnContent("🚀 E*", "number", False)
+    e_2 = ColumnContent("🚀 E_NI_T", "number", False)
+    e_3 = ColumnContent("🚀 E_NI_S", "number", False)
+