Spaces:
Build error
Build error
Maxwell Lyu commited on
Commit ·
bcf4698
0
Parent(s):
init
Browse files- .gitignore +4 -0
- app.py +222 -0
- content.py +20 -0
- data/raw_scores.csv +721 -0
.gitignore
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
.vscode/
|
| 2 |
+
.env/
|
| 3 |
+
debug/
|
| 4 |
+
__pycache__/
|
app.py
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
from dataclasses import dataclass, field, fields
|
| 3 |
+
from functools import cached_property
|
| 4 |
+
from pathlib import Path
|
| 5 |
+
from typing import Literal
|
| 6 |
+
from functools import partial
|
| 7 |
+
from content import *
|
| 8 |
+
|
| 9 |
+
import gradio as gr
|
| 10 |
+
import numpy as np
|
| 11 |
+
import pandas as pd
|
| 12 |
+
import plotly.graph_objects as go
|
| 13 |
+
import pandas as pd
|
| 14 |
+
|
| 15 |
+
# This dataframe must contain the following columns:
|
| 16 |
+
# - model: the name of the model
|
| 17 |
+
# - language: the language of the model
|
| 18 |
+
# - dataset: the dataset used to evaluate the model
|
| 19 |
+
# - score: the score of the model on the (language, dataset) pair
|
| 20 |
+
# - model_type: the type of the model (e.g. "Chat Model", "Base Model")
|
| 21 |
+
df = pd.read_csv("data/raw_scores.csv")
|
| 22 |
+
choices_language = list(df["language"].unique())
|
| 23 |
+
choices_dataset = list(df["dataset"].unique())
|
| 24 |
+
choices_model_type = list(df["model_type"].unique())
|
| 25 |
+
|
| 26 |
+
# Utility functions for data processing
|
| 27 |
+
reduce_functions = {
|
| 28 |
+
"Mean": lambda x: np.mean(x),
|
| 29 |
+
"Median": lambda x: np.median(x),
|
| 30 |
+
"Max": lambda x: np.max(x),
|
| 31 |
+
"Min": lambda x: np.min(x),
|
| 32 |
+
}
|
| 33 |
+
map_functions = {
|
| 34 |
+
"Raw": lambda x: x,
|
| 35 |
+
"Rank": partial(pd.Series.rank, ascending=False, method="dense"),
|
| 36 |
+
"Normalize": lambda x: (x - np.min(x)) / (np.max(x) - np.min(x)),
|
| 37 |
+
}
|
| 38 |
+
score_ascending = {
|
| 39 |
+
"Raw": False,
|
| 40 |
+
"Rank": True,
|
| 41 |
+
"Normalize": False,
|
| 42 |
+
}
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
def prepare_dataframe(
|
| 46 |
+
df: pd.DataFrame,
|
| 47 |
+
filters: dict[str, list[str]],
|
| 48 |
+
group_by: Literal["language", "dataset"],
|
| 49 |
+
map_function: str,
|
| 50 |
+
reduce_function: str,
|
| 51 |
+
) -> pd.DataFrame:
|
| 52 |
+
# Filters contains a value subset for each column
|
| 53 |
+
language = filters["language"]
|
| 54 |
+
dataset = filters["dataset"]
|
| 55 |
+
|
| 56 |
+
# Columns are divided into two groups: other_columns and group_by_columns, apart from `model` which should be the index
|
| 57 |
+
other_columns = list(set(df.columns) - set(["language", "dataset", "score"]))
|
| 58 |
+
group_by_columns = filters[group_by]
|
| 59 |
+
|
| 60 |
+
# Step 1: Filter the dataframe based on the selected language and dataset
|
| 61 |
+
for k, v in filters.items():
|
| 62 |
+
df = df[df[k].isin(v)]
|
| 63 |
+
# If dataframe is empty, return an empty dataframe
|
| 64 |
+
if len(df) == 0:
|
| 65 |
+
gr.Warning(
|
| 66 |
+
f"No scores remain after the filter application. Please verify the checkboxes."
|
| 67 |
+
)
|
| 68 |
+
return pd.DataFrame(columns=other_columns)
|
| 69 |
+
# Sanity check: All score exists for each (language,dataset) pair
|
| 70 |
+
score_count = (
|
| 71 |
+
df.drop_duplicates(subset=["model", "language", "dataset"])
|
| 72 |
+
.groupby(["model"])["score"]
|
| 73 |
+
.count()
|
| 74 |
+
)
|
| 75 |
+
invalid_models = score_count[
|
| 76 |
+
score_count < len(language) * len(dataset)
|
| 77 |
+
].index.tolist()
|
| 78 |
+
df = df[~df["model"].isin(invalid_models)]
|
| 79 |
+
# Send a warning message if there are any invalid models
|
| 80 |
+
for model in invalid_models:
|
| 81 |
+
gr.Warning(
|
| 82 |
+
f"<strong>{model}</strong> is lacking some scores thus hidden. Please report to the maintainers."
|
| 83 |
+
)
|
| 84 |
+
|
| 85 |
+
# Step 2: Process Scores
|
| 86 |
+
# Step 2.0: Map the scores along each (language, dataset) pair
|
| 87 |
+
df["score"] = df.groupby(["language", "dataset"])["score"].transform(
|
| 88 |
+
map_functions[map_function]
|
| 89 |
+
)
|
| 90 |
+
# Step 2.1: Reduce the scores along the column other than `group_by`
|
| 91 |
+
df = (
|
| 92 |
+
df.groupby(other_columns + [group_by])
|
| 93 |
+
.agg({"score": reduce_functions[reduce_function]})
|
| 94 |
+
.reset_index()
|
| 95 |
+
)
|
| 96 |
+
# Step 2.2: Reduce the scores along `group_by` to get the overall score of each model
|
| 97 |
+
reduced_col = df.groupby(other_columns).agg(
|
| 98 |
+
{"score": reduce_functions[reduce_function]}
|
| 99 |
+
)["score"]
|
| 100 |
+
# Step 2.3: Pivot the dataframe, then concat the overall score
|
| 101 |
+
df = df.pivot(index=other_columns, columns=group_by, values=["score"]).droplevel(
|
| 102 |
+
0, 1
|
| 103 |
+
)
|
| 104 |
+
df["Overall Score"] = reduced_col
|
| 105 |
+
|
| 106 |
+
# Step 3: Styling for display
|
| 107 |
+
# - Sort the dataframe by the reduced score
|
| 108 |
+
# - Sort the columns for better readability
|
| 109 |
+
# - Highlight the maximum value in each column
|
| 110 |
+
# - Format the score to 2 decimal places if it is a float
|
| 111 |
+
other_columns.remove("model")
|
| 112 |
+
df = (
|
| 113 |
+
df.reset_index()[
|
| 114 |
+
["model"] + other_columns + ["Overall Score"] + group_by_columns
|
| 115 |
+
]
|
| 116 |
+
.sort_values(by="Overall Score", ascending=score_ascending[map_function])
|
| 117 |
+
.style.format(precision=2)
|
| 118 |
+
)
|
| 119 |
+
if score_ascending[map_function]:
|
| 120 |
+
df = df.highlight_min(
|
| 121 |
+
axis=0, color="#18864B", subset=["Overall Score"] + group_by_columns
|
| 122 |
+
)
|
| 123 |
+
else:
|
| 124 |
+
df = df.highlight_max(
|
| 125 |
+
axis=0, color="#18864B", subset=["Overall Score"] + group_by_columns
|
| 126 |
+
)
|
| 127 |
+
return df
|
| 128 |
+
|
| 129 |
+
|
| 130 |
+
with gr.Blocks(theme=gr.themes.Base()) as demo:
|
| 131 |
+
|
| 132 |
+
gr.Markdown(
|
| 133 |
+
MARKDOWN_HEADER
|
| 134 |
+
)
|
| 135 |
+
|
| 136 |
+
with gr.Column():
|
| 137 |
+
# UI definition
|
| 138 |
+
checkbox_language = gr.CheckboxGroup(
|
| 139 |
+
choices=choices_language,
|
| 140 |
+
value=choices_language,
|
| 141 |
+
label="Language(s)",
|
| 142 |
+
interactive=True,
|
| 143 |
+
)
|
| 144 |
+
checkbox_dataset = gr.CheckboxGroup(
|
| 145 |
+
choices=choices_dataset,
|
| 146 |
+
value=choices_dataset,
|
| 147 |
+
label="Dataset(s)",
|
| 148 |
+
interactive=True,
|
| 149 |
+
)
|
| 150 |
+
checkbox_model_type = gr.CheckboxGroup(
|
| 151 |
+
choices=choices_model_type,
|
| 152 |
+
value=choices_model_type,
|
| 153 |
+
label="Model Type(s)",
|
| 154 |
+
interactive=True,
|
| 155 |
+
)
|
| 156 |
+
dropdown_map_function = gr.Dropdown(
|
| 157 |
+
choices=map_functions.keys(),
|
| 158 |
+
value="Raw",
|
| 159 |
+
label="Map Function",
|
| 160 |
+
interactive=True,
|
| 161 |
+
info=MARKDOWN_MAP_FUNCTION
|
| 162 |
+
)
|
| 163 |
+
dropdown_reduce_function = gr.Dropdown(
|
| 164 |
+
choices=reduce_functions.keys(),
|
| 165 |
+
value="Mean",
|
| 166 |
+
label="Reduce Function",
|
| 167 |
+
interactive=True,
|
| 168 |
+
info=MARKDOWN_REDUCE_FUNCTION
|
| 169 |
+
)
|
| 170 |
+
ratio_group_by = gr.Radio(
|
| 171 |
+
choices=["language", "dataset"],
|
| 172 |
+
value="language",
|
| 173 |
+
label="Group by",
|
| 174 |
+
interactive=True,
|
| 175 |
+
)
|
| 176 |
+
|
| 177 |
+
dataframe = gr.DataFrame(
|
| 178 |
+
prepare_dataframe(
|
| 179 |
+
df=df,
|
| 180 |
+
filters={
|
| 181 |
+
"language": choices_language,
|
| 182 |
+
"dataset": choices_dataset,
|
| 183 |
+
},
|
| 184 |
+
group_by="language",
|
| 185 |
+
map_function="Raw",
|
| 186 |
+
reduce_function="Mean",
|
| 187 |
+
)
|
| 188 |
+
)
|
| 189 |
+
# Event listeners
|
| 190 |
+
gr.on(
|
| 191 |
+
triggers=[
|
| 192 |
+
checkbox_model_type.change,
|
| 193 |
+
checkbox_language.change,
|
| 194 |
+
checkbox_dataset.change,
|
| 195 |
+
ratio_group_by.change,
|
| 196 |
+
dropdown_reduce_function.change,
|
| 197 |
+
dropdown_map_function.change,
|
| 198 |
+
],
|
| 199 |
+
fn=lambda model_type, language, dataset, group_by, map_function, reduce_function: prepare_dataframe(
|
| 200 |
+
df=df,
|
| 201 |
+
filters={
|
| 202 |
+
"language": language,
|
| 203 |
+
"dataset": dataset,
|
| 204 |
+
"model_type": model_type,
|
| 205 |
+
},
|
| 206 |
+
group_by=group_by,
|
| 207 |
+
map_function=map_function,
|
| 208 |
+
reduce_function=reduce_function,
|
| 209 |
+
),
|
| 210 |
+
inputs=[
|
| 211 |
+
checkbox_model_type,
|
| 212 |
+
checkbox_language,
|
| 213 |
+
checkbox_dataset,
|
| 214 |
+
ratio_group_by,
|
| 215 |
+
dropdown_map_function,
|
| 216 |
+
dropdown_reduce_function,
|
| 217 |
+
],
|
| 218 |
+
outputs=[dataframe],
|
| 219 |
+
)
|
| 220 |
+
|
| 221 |
+
if __name__ == "__main__":
|
| 222 |
+
demo.launch(debug=True, server_port=7899)
|
content.py
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MARKDOWN_HEADER = (
|
| 2 |
+
"# M-YASS\n<u>M</u>ultilingual - <u>Y</u>et <u>A</u>nother <u>S</u>ynergistic <u>S</u>core\n"
|
| 3 |
+
"1. Filter: a subset of Language, Dataset and Model Type;\n"
|
| 4 |
+
"2. Map Function: Each score will be mapped within each `<language,dataset>` pair. Can be used to get rank or normalize score;\n"
|
| 5 |
+
"3. Reduce Function: An array of scores will be reduced to one. Can be used to get the average score;\n"
|
| 6 |
+
"4. Group By: Language or Dataset. If `language` is selected, the score of all tasks within this language will be reduced by `Reduce Function`\n"
|
| 7 |
+
)
|
| 8 |
+
|
| 9 |
+
MARKDOWN_MAP_FUNCTION = (
|
| 10 |
+
"Raw: `lambda x: x`\n"
|
| 11 |
+
"Rank: `partial(pd.Series.rank, ascending=False, method='dense')`\n"
|
| 12 |
+
"Normalize: `lambda x: (x - np.min(x)) / (np.max(x) - np.min(x))`\n"
|
| 13 |
+
)
|
| 14 |
+
|
| 15 |
+
MARKDOWN_REDUCE_FUNCTION = (
|
| 16 |
+
"Mean: `lambda x: np.mean(x)`\n"
|
| 17 |
+
"Median: `lambda x: np.median(x)`\n"
|
| 18 |
+
"Max: `lambda x: np.max(x)`\n"
|
| 19 |
+
"Min: `lambda x: np.min(x)`\n"
|
| 20 |
+
)
|
data/raw_scores.csv
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model,model_type,language,dataset,score
|
| 2 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,English,Interpreter,83.2
|
| 3 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,Chinese,Interpreter,76.05
|
| 4 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,Japanese,Interpreter,73.59
|
| 5 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,French,Interpreter,61.54
|
| 6 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,English,Script,58.15
|
| 7 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,Chinese,Script,26.98
|
| 8 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,Japanese,Script,46.04
|
| 9 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,French,Script,52.73
|
| 10 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,English,Compile,58.12
|
| 11 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,Chinese,Compile,73.69
|
| 12 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,Japanese,Compile,81.95
|
| 13 |
+
Qwen2.5-Coder-32B-Instruct,Chat Model,French,Compile,68.53
|
| 14 |
+
Qwen2.5-Coder-32B,Base Model,English,Interpreter,57.1
|
| 15 |
+
Qwen2.5-Coder-32B,Base Model,Chinese,Interpreter,65.07
|
| 16 |
+
Qwen2.5-Coder-32B,Base Model,Japanese,Interpreter,62.7
|
| 17 |
+
Qwen2.5-Coder-32B,Base Model,French,Interpreter,47.93
|
| 18 |
+
Qwen2.5-Coder-32B,Base Model,English,Script,51.28
|
| 19 |
+
Qwen2.5-Coder-32B,Base Model,Chinese,Script,32.3
|
| 20 |
+
Qwen2.5-Coder-32B,Base Model,Japanese,Script,57.25
|
| 21 |
+
Qwen2.5-Coder-32B,Base Model,French,Script,31.2
|
| 22 |
+
Qwen2.5-Coder-32B,Base Model,English,Compile,60.21
|
| 23 |
+
Qwen2.5-Coder-32B,Base Model,Chinese,Compile,65.49
|
| 24 |
+
Qwen2.5-Coder-32B,Base Model,Japanese,Compile,64.35
|
| 25 |
+
Qwen2.5-Coder-32B,Base Model,French,Compile,65.94
|
| 26 |
+
OpenCodeInterpreter-DS-33B,Chat Model,English,Interpreter,75.23
|
| 27 |
+
OpenCodeInterpreter-DS-33B,Chat Model,Chinese,Interpreter,69.06
|
| 28 |
+
OpenCodeInterpreter-DS-33B,Chat Model,Japanese,Interpreter,59.32
|
| 29 |
+
OpenCodeInterpreter-DS-33B,Chat Model,French,Interpreter,34.55
|
| 30 |
+
OpenCodeInterpreter-DS-33B,Chat Model,English,Script,46.58
|
| 31 |
+
OpenCodeInterpreter-DS-33B,Chat Model,Chinese,Script,22.31
|
| 32 |
+
OpenCodeInterpreter-DS-33B,Chat Model,Japanese,Script,57.76
|
| 33 |
+
OpenCodeInterpreter-DS-33B,Chat Model,French,Script,45.94
|
| 34 |
+
OpenCodeInterpreter-DS-33B,Chat Model,English,Compile,51.85
|
| 35 |
+
OpenCodeInterpreter-DS-33B,Chat Model,Chinese,Compile,54.8
|
| 36 |
+
OpenCodeInterpreter-DS-33B,Chat Model,Japanese,Compile,64.47
|
| 37 |
+
OpenCodeInterpreter-DS-33B,Chat Model,French,Compile,57.95
|
| 38 |
+
Nxcode-CQ-7B-orpo,Chat Model,English,Interpreter,87.23
|
| 39 |
+
Nxcode-CQ-7B-orpo,Chat Model,Chinese,Interpreter,71.69
|
| 40 |
+
Nxcode-CQ-7B-orpo,Chat Model,Japanese,Interpreter,67.98
|
| 41 |
+
Nxcode-CQ-7B-orpo,Chat Model,French,Interpreter,32.26
|
| 42 |
+
Nxcode-CQ-7B-orpo,Chat Model,English,Script,50.54
|
| 43 |
+
Nxcode-CQ-7B-orpo,Chat Model,Chinese,Script,23.22
|
| 44 |
+
Nxcode-CQ-7B-orpo,Chat Model,Japanese,Script,37.24
|
| 45 |
+
Nxcode-CQ-7B-orpo,Chat Model,French,Script,39.73
|
| 46 |
+
Nxcode-CQ-7B-orpo,Chat Model,English,Compile,58.51
|
| 47 |
+
Nxcode-CQ-7B-orpo,Chat Model,Chinese,Compile,60.91
|
| 48 |
+
Nxcode-CQ-7B-orpo,Chat Model,Japanese,Compile,68.04
|
| 49 |
+
Nxcode-CQ-7B-orpo,Chat Model,French,Compile,65.53
|
| 50 |
+
CodeQwen1.5-7B-Chat,Chat Model,English,Interpreter,87.2
|
| 51 |
+
CodeQwen1.5-7B-Chat,Chat Model,Chinese,Interpreter,70.31
|
| 52 |
+
CodeQwen1.5-7B-Chat,Chat Model,Japanese,Interpreter,69.22
|
| 53 |
+
CodeQwen1.5-7B-Chat,Chat Model,French,Interpreter,29.38
|
| 54 |
+
CodeQwen1.5-7B-Chat,Chat Model,English,Script,51.89
|
| 55 |
+
CodeQwen1.5-7B-Chat,Chat Model,Chinese,Script,22.71
|
| 56 |
+
CodeQwen1.5-7B-Chat,Chat Model,Japanese,Script,32.89
|
| 57 |
+
CodeQwen1.5-7B-Chat,Chat Model,French,Script,39.86
|
| 58 |
+
CodeQwen1.5-7B-Chat,Chat Model,English,Compile,59.59
|
| 59 |
+
CodeQwen1.5-7B-Chat,Chat Model,Chinese,Compile,61.04
|
| 60 |
+
CodeQwen1.5-7B-Chat,Chat Model,Japanese,Compile,67.85
|
| 61 |
+
CodeQwen1.5-7B-Chat,Chat Model,French,Compile,67.49
|
| 62 |
+
CodeFuse-DeepSeek-33b,Chat Model,English,Interpreter,76.83
|
| 63 |
+
CodeFuse-DeepSeek-33b,Chat Model,Chinese,Interpreter,66.46
|
| 64 |
+
CodeFuse-DeepSeek-33b,Chat Model,Japanese,Interpreter,57.76
|
| 65 |
+
CodeFuse-DeepSeek-33b,Chat Model,French,Interpreter,34.16
|
| 66 |
+
CodeFuse-DeepSeek-33b,Chat Model,English,Script,38.36
|
| 67 |
+
CodeFuse-DeepSeek-33b,Chat Model,Chinese,Script,24.36
|
| 68 |
+
CodeFuse-DeepSeek-33b,Chat Model,Japanese,Script,52.8
|
| 69 |
+
CodeFuse-DeepSeek-33b,Chat Model,French,Script,40.37
|
| 70 |
+
CodeFuse-DeepSeek-33b,Chat Model,English,Compile,49.37
|
| 71 |
+
CodeFuse-DeepSeek-33b,Chat Model,Chinese,Compile,60.76
|
| 72 |
+
CodeFuse-DeepSeek-33b,Chat Model,Japanese,Compile,65.22
|
| 73 |
+
CodeFuse-DeepSeek-33b,Chat Model,French,Compile,53.85
|
| 74 |
+
DeepSeek-Coder-33b-instruct,Chat Model,English,Interpreter,80.02
|
| 75 |
+
DeepSeek-Coder-33b-instruct,Chat Model,Chinese,Interpreter,65.13
|
| 76 |
+
DeepSeek-Coder-33b-instruct,Chat Model,Japanese,Interpreter,52.5
|
| 77 |
+
DeepSeek-Coder-33b-instruct,Chat Model,French,Interpreter,31.69
|
| 78 |
+
DeepSeek-Coder-33b-instruct,Chat Model,English,Script,42.92
|
| 79 |
+
DeepSeek-Coder-33b-instruct,Chat Model,Chinese,Script,17.85
|
| 80 |
+
DeepSeek-Coder-33b-instruct,Chat Model,Japanese,Script,50.92
|
| 81 |
+
DeepSeek-Coder-33b-instruct,Chat Model,French,Script,39.43
|
| 82 |
+
DeepSeek-Coder-33b-instruct,Chat Model,English,Compile,49.42
|
| 83 |
+
DeepSeek-Coder-33b-instruct,Chat Model,Chinese,Compile,52.03
|
| 84 |
+
DeepSeek-Coder-33b-instruct,Chat Model,Japanese,Compile,62.36
|
| 85 |
+
DeepSeek-Coder-33b-instruct,Chat Model,French,Compile,55.56
|
| 86 |
+
Artigenz-Coder-DS-6.7B,Chat Model,English,Interpreter,70.89
|
| 87 |
+
Artigenz-Coder-DS-6.7B,Chat Model,Chinese,Interpreter,66.16
|
| 88 |
+
Artigenz-Coder-DS-6.7B,Chat Model,Japanese,Interpreter,55.24
|
| 89 |
+
Artigenz-Coder-DS-6.7B,Chat Model,French,Interpreter,30.15
|
| 90 |
+
Artigenz-Coder-DS-6.7B,Chat Model,English,Script,41.94
|
| 91 |
+
Artigenz-Coder-DS-6.7B,Chat Model,Chinese,Script,20.09
|
| 92 |
+
Artigenz-Coder-DS-6.7B,Chat Model,Japanese,Script,44.56
|
| 93 |
+
Artigenz-Coder-DS-6.7B,Chat Model,French,Script,39.94
|
| 94 |
+
Artigenz-Coder-DS-6.7B,Chat Model,English,Compile,43.91
|
| 95 |
+
Artigenz-Coder-DS-6.7B,Chat Model,Chinese,Compile,56.84
|
| 96 |
+
Artigenz-Coder-DS-6.7B,Chat Model,Japanese,Compile,59.75
|
| 97 |
+
Artigenz-Coder-DS-6.7B,Chat Model,French,Compile,48.77
|
| 98 |
+
DeepSeek-Coder-7b-instruct,Chat Model,English,Interpreter,80.22
|
| 99 |
+
DeepSeek-Coder-7b-instruct,Chat Model,Chinese,Interpreter,65.8
|
| 100 |
+
DeepSeek-Coder-7b-instruct,Chat Model,Japanese,Interpreter,59.4
|
| 101 |
+
DeepSeek-Coder-7b-instruct,Chat Model,French,Interpreter,20.87
|
| 102 |
+
DeepSeek-Coder-7b-instruct,Chat Model,English,Script,38.84
|
| 103 |
+
DeepSeek-Coder-7b-instruct,Chat Model,Chinese,Script,21.59
|
| 104 |
+
DeepSeek-Coder-7b-instruct,Chat Model,Japanese,Script,47.78
|
| 105 |
+
DeepSeek-Coder-7b-instruct,Chat Model,French,Script,38.56
|
| 106 |
+
DeepSeek-Coder-7b-instruct,Chat Model,English,Compile,44.22
|
| 107 |
+
DeepSeek-Coder-7b-instruct,Chat Model,Chinese,Compile,53.34
|
| 108 |
+
DeepSeek-Coder-7b-instruct,Chat Model,Japanese,Compile,59.66
|
| 109 |
+
DeepSeek-Coder-7b-instruct,Chat Model,French,Compile,47.73
|
| 110 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,English,Interpreter,73.2
|
| 111 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,Chinese,Interpreter,63.85
|
| 112 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,Japanese,Interpreter,57.34
|
| 113 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,French,Interpreter,24.32
|
| 114 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,English,Script,39.69
|
| 115 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,Chinese,Script,18.22
|
| 116 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,Japanese,Script,44.3
|
| 117 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,French,Script,39.08
|
| 118 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,English,Compile,45.99
|
| 119 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,Chinese,Compile,51.41
|
| 120 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,Japanese,Compile,60.01
|
| 121 |
+
OpenCodeInterpreter-DS-6.7B,Chat Model,French,Compile,48.22
|
| 122 |
+
Phind-CodeLlama-34B-v2,Chat Model,English,Interpreter,71.95
|
| 123 |
+
Phind-CodeLlama-34B-v2,Chat Model,Chinese,Interpreter,65.34
|
| 124 |
+
Phind-CodeLlama-34B-v2,Chat Model,Japanese,Interpreter,56.26
|
| 125 |
+
Phind-CodeLlama-34B-v2,Chat Model,French,Interpreter,28.7
|
| 126 |
+
Phind-CodeLlama-34B-v2,Chat Model,English,Script,45.12
|
| 127 |
+
Phind-CodeLlama-34B-v2,Chat Model,Chinese,Script,14.12
|
| 128 |
+
Phind-CodeLlama-34B-v2,Chat Model,Japanese,Script,44.27
|
| 129 |
+
Phind-CodeLlama-34B-v2,Chat Model,French,Script,37.7
|
| 130 |
+
Phind-CodeLlama-34B-v2,Chat Model,English,Compile,49.63
|
| 131 |
+
Phind-CodeLlama-34B-v2,Chat Model,Chinese,Compile,54.06
|
| 132 |
+
Phind-CodeLlama-34B-v2,Chat Model,Japanese,Compile,59.59
|
| 133 |
+
Phind-CodeLlama-34B-v2,Chat Model,French,Compile,57.67
|
| 134 |
+
Phind-CodeLlama-34B-v1,Chat Model,English,Interpreter,65.85
|
| 135 |
+
Phind-CodeLlama-34B-v1,Chat Model,Chinese,Interpreter,64.45
|
| 136 |
+
Phind-CodeLlama-34B-v1,Chat Model,Japanese,Interpreter,55.53
|
| 137 |
+
Phind-CodeLlama-34B-v1,Chat Model,French,Interpreter,24.89
|
| 138 |
+
Phind-CodeLlama-34B-v1,Chat Model,English,Script,43.23
|
| 139 |
+
Phind-CodeLlama-34B-v1,Chat Model,Chinese,Script,15.5
|
| 140 |
+
Phind-CodeLlama-34B-v1,Chat Model,Japanese,Script,42.05
|
| 141 |
+
Phind-CodeLlama-34B-v1,Chat Model,French,Script,36.71
|
| 142 |
+
Phind-CodeLlama-34B-v1,Chat Model,English,Compile,53.27
|
| 143 |
+
Phind-CodeLlama-34B-v1,Chat Model,Chinese,Compile,49.47
|
| 144 |
+
Phind-CodeLlama-34B-v1,Chat Model,Japanese,Compile,57.81
|
| 145 |
+
Phind-CodeLlama-34B-v1,Chat Model,French,Compile,54.1
|
| 146 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,English,Interpreter,70.22
|
| 147 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,Chinese,Interpreter,66.24
|
| 148 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,Japanese,Interpreter,52.05
|
| 149 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,French,Interpreter,18.88
|
| 150 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,English,Script,44.23
|
| 151 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,Chinese,Script,13.78
|
| 152 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,Japanese,Script,39.44
|
| 153 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,French,Script,37.76
|
| 154 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,English,Compile,47.11
|
| 155 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,Chinese,Compile,48.72
|
| 156 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,Japanese,Compile,55.34
|
| 157 |
+
Phind-CodeLlama-34B-Python-v1,Chat Model,French,Compile,49.22
|
| 158 |
+
CodeQwen1.5-7B,Base Model,English,Interpreter,50.79
|
| 159 |
+
CodeQwen1.5-7B,Base Model,Chinese,Interpreter,50.07
|
| 160 |
+
CodeQwen1.5-7B,Base Model,Japanese,Interpreter,50.92
|
| 161 |
+
CodeQwen1.5-7B,Base Model,French,Interpreter,24.89
|
| 162 |
+
CodeQwen1.5-7B,Base Model,English,Script,37.27
|
| 163 |
+
CodeQwen1.5-7B,Base Model,Chinese,Script,16.03
|
| 164 |
+
CodeQwen1.5-7B,Base Model,Japanese,Script,46.29
|
| 165 |
+
CodeQwen1.5-7B,Base Model,French,Script,27.95
|
| 166 |
+
CodeQwen1.5-7B,Base Model,English,Compile,43.33
|
| 167 |
+
CodeQwen1.5-7B,Base Model,Chinese,Compile,42.15
|
| 168 |
+
CodeQwen1.5-7B,Base Model,Japanese,Compile,48.35
|
| 169 |
+
CodeQwen1.5-7B,Base Model,French,Compile,47.56
|
| 170 |
+
CodeLlama-70b-Instruct,Chat Model,English,Interpreter,75.6
|
| 171 |
+
CodeLlama-70b-Instruct,Chat Model,Chinese,Interpreter,57.76
|
| 172 |
+
CodeLlama-70b-Instruct,Chat Model,Japanese,Interpreter,57.14
|
| 173 |
+
CodeLlama-70b-Instruct,Chat Model,French,Interpreter,0.0
|
| 174 |
+
CodeLlama-70b-Instruct,Chat Model,English,Script,42.24
|
| 175 |
+
CodeLlama-70b-Instruct,Chat Model,Chinese,Script,19.88
|
| 176 |
+
CodeLlama-70b-Instruct,Chat Model,Japanese,Script,44.1
|
| 177 |
+
CodeLlama-70b-Instruct,Chat Model,French,Script,29.19
|
| 178 |
+
CodeLlama-70b-Instruct,Chat Model,English,Compile,42.86
|
| 179 |
+
CodeLlama-70b-Instruct,Chat Model,Chinese,Compile,47.2
|
| 180 |
+
CodeLlama-70b-Instruct,Chat Model,Japanese,Compile,48.45
|
| 181 |
+
CodeLlama-70b-Instruct,Chat Model,French,Compile,47.2
|
| 182 |
+
WizardCoder-Python-34B-V1.0,Chat Model,English,Interpreter,70.73
|
| 183 |
+
WizardCoder-Python-34B-V1.0,Chat Model,Chinese,Interpreter,55.28
|
| 184 |
+
WizardCoder-Python-34B-V1.0,Chat Model,Japanese,Interpreter,47.2
|
| 185 |
+
WizardCoder-Python-34B-V1.0,Chat Model,French,Interpreter,18.63
|
| 186 |
+
WizardCoder-Python-34B-V1.0,Chat Model,English,Script,41.51
|
| 187 |
+
WizardCoder-Python-34B-V1.0,Chat Model,Chinese,Script,15.38
|
| 188 |
+
WizardCoder-Python-34B-V1.0,Chat Model,Japanese,Script,32.3
|
| 189 |
+
WizardCoder-Python-34B-V1.0,Chat Model,French,Script,39.75
|
| 190 |
+
WizardCoder-Python-34B-V1.0,Chat Model,English,Compile,44.3
|
| 191 |
+
WizardCoder-Python-34B-V1.0,Chat Model,Chinese,Compile,44.94
|
| 192 |
+
WizardCoder-Python-34B-V1.0,Chat Model,Japanese,Compile,47.2
|
| 193 |
+
WizardCoder-Python-34B-V1.0,Chat Model,French,Compile,46.15
|
| 194 |
+
CodeLlama-70b,Base Model,English,Interpreter,52.44
|
| 195 |
+
CodeLlama-70b,Base Model,Chinese,Interpreter,56.52
|
| 196 |
+
CodeLlama-70b,Base Model,Japanese,Interpreter,46.58
|
| 197 |
+
CodeLlama-70b,Base Model,French,Interpreter,0.0
|
| 198 |
+
CodeLlama-70b,Base Model,English,Script,42.24
|
| 199 |
+
CodeLlama-70b,Base Model,Chinese,Script,24.84
|
| 200 |
+
CodeLlama-70b,Base Model,Japanese,Script,41.61
|
| 201 |
+
CodeLlama-70b,Base Model,French,Script,27.95
|
| 202 |
+
CodeLlama-70b,Base Model,English,Compile,42.86
|
| 203 |
+
CodeLlama-70b,Base Model,Chinese,Compile,44.72
|
| 204 |
+
CodeLlama-70b,Base Model,Japanese,Compile,49.69
|
| 205 |
+
CodeLlama-70b,Base Model,French,Compile,49.69
|
| 206 |
+
DeepSeek-Coder-33b-base,Base Model,English,Interpreter,52.45
|
| 207 |
+
DeepSeek-Coder-33b-base,Base Model,Chinese,Interpreter,51.28
|
| 208 |
+
DeepSeek-Coder-33b-base,Base Model,Japanese,Interpreter,41.76
|
| 209 |
+
DeepSeek-Coder-33b-base,Base Model,French,Interpreter,23.37
|
| 210 |
+
DeepSeek-Coder-33b-base,Base Model,English,Script,32.83
|
| 211 |
+
DeepSeek-Coder-33b-base,Base Model,Chinese,Script,17.41
|
| 212 |
+
DeepSeek-Coder-33b-base,Base Model,Japanese,Script,36.51
|
| 213 |
+
DeepSeek-Coder-33b-base,Base Model,French,Script,26.76
|
| 214 |
+
DeepSeek-Coder-33b-base,Base Model,English,Compile,35.75
|
| 215 |
+
DeepSeek-Coder-33b-base,Base Model,Chinese,Compile,43.77
|
| 216 |
+
DeepSeek-Coder-33b-base,Base Model,Japanese,Compile,51.22
|
| 217 |
+
DeepSeek-Coder-33b-base,Base Model,French,Compile,43.78
|
| 218 |
+
CodeLlama-70b-Python,Base Model,English,Interpreter,55.49
|
| 219 |
+
CodeLlama-70b-Python,Base Model,Chinese,Interpreter,56.52
|
| 220 |
+
CodeLlama-70b-Python,Base Model,Japanese,Interpreter,52.8
|
| 221 |
+
CodeLlama-70b-Python,Base Model,French,Interpreter,0.0
|
| 222 |
+
CodeLlama-70b-Python,Base Model,English,Script,35.4
|
| 223 |
+
CodeLlama-70b-Python,Base Model,Chinese,Script,21.12
|
| 224 |
+
CodeLlama-70b-Python,Base Model,Japanese,Script,44.72
|
| 225 |
+
CodeLlama-70b-Python,Base Model,French,Script,26.09
|
| 226 |
+
CodeLlama-70b-Python,Base Model,English,Compile,39.13
|
| 227 |
+
CodeLlama-70b-Python,Base Model,Chinese,Compile,45.96
|
| 228 |
+
CodeLlama-70b-Python,Base Model,Japanese,Compile,49.69
|
| 229 |
+
CodeLlama-70b-Python,Base Model,French,Compile,48.45
|
| 230 |
+
StarCoder2-15B,Base Model,English,Interpreter,44.15
|
| 231 |
+
StarCoder2-15B,Base Model,Chinese,Interpreter,44.24
|
| 232 |
+
StarCoder2-15B,Base Model,Japanese,Interpreter,39.48
|
| 233 |
+
StarCoder2-15B,Base Model,French,Interpreter,22.41
|
| 234 |
+
StarCoder2-15B,Base Model,English,Script,33.19
|
| 235 |
+
StarCoder2-15B,Base Model,Chinese,Script,23.64
|
| 236 |
+
StarCoder2-15B,Base Model,Japanese,Script,43.75
|
| 237 |
+
StarCoder2-15B,Base Model,French,Script,19.81
|
| 238 |
+
StarCoder2-15B,Base Model,English,Compile,34.18
|
| 239 |
+
StarCoder2-15B,Base Model,Chinese,Compile,33.86
|
| 240 |
+
StarCoder2-15B,Base Model,Japanese,Compile,41.44
|
| 241 |
+
StarCoder2-15B,Base Model,French,Compile,38.03
|
| 242 |
+
CodeLlama-34b-Instruct,Chat Model,English,Interpreter,50.79
|
| 243 |
+
CodeLlama-34b-Instruct,Chat Model,Chinese,Interpreter,45.85
|
| 244 |
+
CodeLlama-34b-Instruct,Chat Model,Japanese,Interpreter,36.98
|
| 245 |
+
CodeLlama-34b-Instruct,Chat Model,French,Interpreter,18.09
|
| 246 |
+
CodeLlama-34b-Instruct,Chat Model,English,Script,32.65
|
| 247 |
+
CodeLlama-34b-Instruct,Chat Model,Chinese,Script,13.63
|
| 248 |
+
CodeLlama-34b-Instruct,Chat Model,Japanese,Script,38.87
|
| 249 |
+
CodeLlama-34b-Instruct,Chat Model,French,Script,24.25
|
| 250 |
+
CodeLlama-34b-Instruct,Chat Model,English,Compile,37.63
|
| 251 |
+
CodeLlama-34b-Instruct,Chat Model,Chinese,Compile,41.53
|
| 252 |
+
CodeLlama-34b-Instruct,Chat Model,Japanese,Compile,41.53
|
| 253 |
+
CodeLlama-34b-Instruct,Chat Model,French,Compile,39.26
|
| 254 |
+
WizardCoder-Python-13B-V1.0,Chat Model,English,Interpreter,62.19
|
| 255 |
+
WizardCoder-Python-13B-V1.0,Chat Model,Chinese,Interpreter,48.45
|
| 256 |
+
WizardCoder-Python-13B-V1.0,Chat Model,Japanese,Interpreter,42.24
|
| 257 |
+
WizardCoder-Python-13B-V1.0,Chat Model,French,Interpreter,16.15
|
| 258 |
+
WizardCoder-Python-13B-V1.0,Chat Model,English,Script,38.99
|
| 259 |
+
WizardCoder-Python-13B-V1.0,Chat Model,Chinese,Script,11.54
|
| 260 |
+
WizardCoder-Python-13B-V1.0,Chat Model,Japanese,Script,32.92
|
| 261 |
+
WizardCoder-Python-13B-V1.0,Chat Model,French,Script,27.33
|
| 262 |
+
WizardCoder-Python-13B-V1.0,Chat Model,English,Compile,32.28
|
| 263 |
+
WizardCoder-Python-13B-V1.0,Chat Model,Chinese,Compile,41.77
|
| 264 |
+
WizardCoder-Python-13B-V1.0,Chat Model,Japanese,Compile,42.86
|
| 265 |
+
WizardCoder-Python-13B-V1.0,Chat Model,French,Compile,34.62
|
| 266 |
+
DeepSeek-Coder-7b-base,Base Model,English,Interpreter,45.83
|
| 267 |
+
DeepSeek-Coder-7b-base,Base Model,Chinese,Interpreter,45.9
|
| 268 |
+
DeepSeek-Coder-7b-base,Base Model,Japanese,Interpreter,36.92
|
| 269 |
+
DeepSeek-Coder-7b-base,Base Model,French,Interpreter,18.73
|
| 270 |
+
DeepSeek-Coder-7b-base,Base Model,English,Script,28.74
|
| 271 |
+
DeepSeek-Coder-7b-base,Base Model,Chinese,Script,19.74
|
| 272 |
+
DeepSeek-Coder-7b-base,Base Model,Japanese,Script,33.89
|
| 273 |
+
DeepSeek-Coder-7b-base,Base Model,French,Script,28.99
|
| 274 |
+
DeepSeek-Coder-7b-base,Base Model,English,Compile,25.8
|
| 275 |
+
DeepSeek-Coder-7b-base,Base Model,Chinese,Compile,37.72
|
| 276 |
+
DeepSeek-Coder-7b-base,Base Model,Japanese,Compile,45.53
|
| 277 |
+
DeepSeek-Coder-7b-base,Base Model,French,Compile,34.67
|
| 278 |
+
CodeLlama-34b,Base Model,English,Interpreter,45.11
|
| 279 |
+
CodeLlama-34b,Base Model,Chinese,Interpreter,41.66
|
| 280 |
+
CodeLlama-34b,Base Model,Japanese,Interpreter,40.43
|
| 281 |
+
CodeLlama-34b,Base Model,French,Interpreter,16.94
|
| 282 |
+
CodeLlama-34b,Base Model,English,Script,31.4
|
| 283 |
+
CodeLlama-34b,Base Model,Chinese,Script,15.27
|
| 284 |
+
CodeLlama-34b,Base Model,Japanese,Script,37.49
|
| 285 |
+
CodeLlama-34b,Base Model,French,Script,22.71
|
| 286 |
+
CodeLlama-34b,Base Model,English,Compile,35.28
|
| 287 |
+
CodeLlama-34b,Base Model,Chinese,Compile,40.19
|
| 288 |
+
CodeLlama-34b,Base Model,Japanese,Compile,41.42
|
| 289 |
+
CodeLlama-34b,Base Model,French,Compile,38.73
|
| 290 |
+
CodeLlama-34b-Python,Base Model,English,Interpreter,53.29
|
| 291 |
+
CodeLlama-34b-Python,Base Model,Chinese,Interpreter,44.72
|
| 292 |
+
CodeLlama-34b-Python,Base Model,Japanese,Interpreter,39.78
|
| 293 |
+
CodeLlama-34b-Python,Base Model,French,Interpreter,13.19
|
| 294 |
+
CodeLlama-34b-Python,Base Model,English,Script,31.37
|
| 295 |
+
CodeLlama-34b-Python,Base Model,Chinese,Script,17.29
|
| 296 |
+
CodeLlama-34b-Python,Base Model,Japanese,Script,31.9
|
| 297 |
+
CodeLlama-34b-Python,Base Model,French,Script,22.35
|
| 298 |
+
CodeLlama-34b-Python,Base Model,English,Compile,34.3
|
| 299 |
+
CodeLlama-34b-Python,Base Model,Chinese,Compile,39.46
|
| 300 |
+
CodeLlama-34b-Python,Base Model,Japanese,Compile,39.09
|
| 301 |
+
CodeLlama-34b-Python,Base Model,French,Compile,39.67
|
| 302 |
+
WizardCoder-15B-V1.0,Chat Model,English,Interpreter,58.12
|
| 303 |
+
WizardCoder-15B-V1.0,Chat Model,Chinese,Interpreter,41.91
|
| 304 |
+
WizardCoder-15B-V1.0,Chat Model,Japanese,Interpreter,39.34
|
| 305 |
+
WizardCoder-15B-V1.0,Chat Model,French,Interpreter,13.39
|
| 306 |
+
WizardCoder-15B-V1.0,Chat Model,English,Script,33.98
|
| 307 |
+
WizardCoder-15B-V1.0,Chat Model,Chinese,Script,12.14
|
| 308 |
+
WizardCoder-15B-V1.0,Chat Model,Japanese,Script,27.85
|
| 309 |
+
WizardCoder-15B-V1.0,Chat Model,French,Script,22.53
|
| 310 |
+
WizardCoder-15B-V1.0,Chat Model,English,Compile,27.06
|
| 311 |
+
WizardCoder-15B-V1.0,Chat Model,Chinese,Compile,35.77
|
| 312 |
+
WizardCoder-15B-V1.0,Chat Model,Japanese,Compile,38.95
|
| 313 |
+
WizardCoder-15B-V1.0,Chat Model,French,Compile,33.74
|
| 314 |
+
CodeLlama-13b-Instruct,Chat Model,English,Interpreter,50.6
|
| 315 |
+
CodeLlama-13b-Instruct,Chat Model,Chinese,Interpreter,40.92
|
| 316 |
+
CodeLlama-13b-Instruct,Chat Model,Japanese,Interpreter,32.07
|
| 317 |
+
CodeLlama-13b-Instruct,Chat Model,French,Interpreter,16.66
|
| 318 |
+
CodeLlama-13b-Instruct,Chat Model,English,Script,32.23
|
| 319 |
+
CodeLlama-13b-Instruct,Chat Model,Chinese,Script,16.29
|
| 320 |
+
CodeLlama-13b-Instruct,Chat Model,Japanese,Script,31.6
|
| 321 |
+
CodeLlama-13b-Instruct,Chat Model,French,Script,20.14
|
| 322 |
+
CodeLlama-13b-Instruct,Chat Model,English,Compile,31.75
|
| 323 |
+
CodeLlama-13b-Instruct,Chat Model,Chinese,Compile,33.99
|
| 324 |
+
CodeLlama-13b-Instruct,Chat Model,Japanese,Compile,36.36
|
| 325 |
+
CodeLlama-13b-Instruct,Chat Model,French,Compile,32.82
|
| 326 |
+
CodeGemma-7B,Base Model,English,Interpreter,40.13
|
| 327 |
+
CodeGemma-7B,Base Model,Chinese,Interpreter,43.06
|
| 328 |
+
CodeGemma-7B,Base Model,Japanese,Interpreter,34.76
|
| 329 |
+
CodeGemma-7B,Base Model,French,Interpreter,13.55
|
| 330 |
+
CodeGemma-7B,Base Model,English,Script,28.91
|
| 331 |
+
CodeGemma-7B,Base Model,Chinese,Script,10.44
|
| 332 |
+
CodeGemma-7B,Base Model,Japanese,Script,32.88
|
| 333 |
+
CodeGemma-7B,Base Model,French,Script,20.96
|
| 334 |
+
CodeGemma-7B,Base Model,English,Compile,32.62
|
| 335 |
+
CodeGemma-7B,Base Model,Chinese,Compile,35.03
|
| 336 |
+
CodeGemma-7B,Base Model,Japanese,Compile,40.34
|
| 337 |
+
CodeGemma-7B,Base Model,French,Compile,34.56
|
| 338 |
+
CodeLlama-13b,Base Model,English,Interpreter,35.07
|
| 339 |
+
CodeLlama-13b,Base Model,Chinese,Interpreter,38.26
|
| 340 |
+
CodeLlama-13b,Base Model,Japanese,Interpreter,32.57
|
| 341 |
+
CodeLlama-13b,Base Model,French,Interpreter,13.63
|
| 342 |
+
CodeLlama-13b,Base Model,English,Script,28.01
|
| 343 |
+
CodeLlama-13b,Base Model,Chinese,Script,15.78
|
| 344 |
+
CodeLlama-13b,Base Model,Japanese,Script,31.26
|
| 345 |
+
CodeLlama-13b,Base Model,French,Script,18.32
|
| 346 |
+
CodeLlama-13b,Base Model,English,Compile,29.54
|
| 347 |
+
CodeLlama-13b,Base Model,Chinese,Compile,32.23
|
| 348 |
+
CodeLlama-13b,Base Model,Japanese,Compile,35.81
|
| 349 |
+
CodeLlama-13b,Base Model,French,Compile,29.72
|
| 350 |
+
CodeLlama-13b-Python,Base Model,English,Interpreter,42.89
|
| 351 |
+
CodeLlama-13b-Python,Base Model,Chinese,Interpreter,40.66
|
| 352 |
+
CodeLlama-13b-Python,Base Model,Japanese,Interpreter,34.55
|
| 353 |
+
CodeLlama-13b-Python,Base Model,French,Interpreter,12.51
|
| 354 |
+
CodeLlama-13b-Python,Base Model,English,Script,30.4
|
| 355 |
+
CodeLlama-13b-Python,Base Model,Chinese,Script,9.82
|
| 356 |
+
CodeLlama-13b-Python,Base Model,Japanese,Script,29.9
|
| 357 |
+
CodeLlama-13b-Python,Base Model,French,Script,18.35
|
| 358 |
+
CodeLlama-13b-Python,Base Model,English,Compile,25.85
|
| 359 |
+
CodeLlama-13b-Python,Base Model,Chinese,Compile,33.56
|
| 360 |
+
CodeLlama-13b-Python,Base Model,Japanese,Compile,36.21
|
| 361 |
+
CodeLlama-13b-Python,Base Model,French,Compile,29.32
|
| 362 |
+
CodeLlama-7b-Instruct,Chat Model,English,Interpreter,45.65
|
| 363 |
+
CodeLlama-7b-Instruct,Chat Model,Chinese,Interpreter,33.11
|
| 364 |
+
CodeLlama-7b-Instruct,Chat Model,Japanese,Interpreter,28.55
|
| 365 |
+
CodeLlama-7b-Instruct,Chat Model,French,Interpreter,11.81
|
| 366 |
+
CodeLlama-7b-Instruct,Chat Model,English,Script,27.58
|
| 367 |
+
CodeLlama-7b-Instruct,Chat Model,Chinese,Script,11.81
|
| 368 |
+
CodeLlama-7b-Instruct,Chat Model,Japanese,Script,30.47
|
| 369 |
+
CodeLlama-7b-Instruct,Chat Model,French,Script,19.7
|
| 370 |
+
CodeLlama-7b-Instruct,Chat Model,English,Compile,26.66
|
| 371 |
+
CodeLlama-7b-Instruct,Chat Model,Chinese,Compile,28.77
|
| 372 |
+
CodeLlama-7b-Instruct,Chat Model,Japanese,Compile,29.03
|
| 373 |
+
CodeLlama-7b-Instruct,Chat Model,French,Compile,24.27
|
| 374 |
+
StarCoder2-7B,Base Model,English,Interpreter,34.09
|
| 375 |
+
StarCoder2-7B,Base Model,Chinese,Interpreter,35.35
|
| 376 |
+
StarCoder2-7B,Base Model,Japanese,Interpreter,30.58
|
| 377 |
+
StarCoder2-7B,Base Model,French,Interpreter,11.58
|
| 378 |
+
StarCoder2-7B,Base Model,English,Script,20.42
|
| 379 |
+
StarCoder2-7B,Base Model,Chinese,Script,15.12
|
| 380 |
+
StarCoder2-7B,Base Model,Japanese,Script,30.67
|
| 381 |
+
StarCoder2-7B,Base Model,French,Script,16.72
|
| 382 |
+
StarCoder2-7B,Base Model,English,Compile,26.06
|
| 383 |
+
StarCoder2-7B,Base Model,Chinese,Compile,29.42
|
| 384 |
+
StarCoder2-7B,Base Model,Japanese,Compile,33.63
|
| 385 |
+
StarCoder2-7B,Base Model,French,Compile,29.62
|
| 386 |
+
CodeGemma-7B-it,Chat Model,English,Interpreter,52.74
|
| 387 |
+
CodeGemma-7B-it,Chat Model,Chinese,Interpreter,47.71
|
| 388 |
+
CodeGemma-7B-it,Chat Model,Japanese,Interpreter,19.18
|
| 389 |
+
CodeGemma-7B-it,Chat Model,French,Interpreter,9.22
|
| 390 |
+
CodeGemma-7B-it,Chat Model,English,Script,19.56
|
| 391 |
+
CodeGemma-7B-it,Chat Model,Chinese,Script,11.83
|
| 392 |
+
CodeGemma-7B-it,Chat Model,Japanese,Script,22.02
|
| 393 |
+
CodeGemma-7B-it,Chat Model,French,Script,21.64
|
| 394 |
+
CodeGemma-7B-it,Chat Model,English,Compile,6.91
|
| 395 |
+
CodeGemma-7B-it,Chat Model,Chinese,Compile,41.42
|
| 396 |
+
CodeGemma-7B-it,Chat Model,Japanese,Compile,42.6
|
| 397 |
+
CodeGemma-7B-it,Chat Model,French,Compile,38.31
|
| 398 |
+
CodeShell-7B,Chat Model,English,Interpreter,34.32
|
| 399 |
+
CodeShell-7B,Chat Model,Chinese,Interpreter,33.17
|
| 400 |
+
CodeShell-7B,Chat Model,Japanese,Interpreter,30.87
|
| 401 |
+
CodeShell-7B,Chat Model,French,Interpreter,17.2
|
| 402 |
+
CodeShell-7B,Chat Model,English,Script,22.08
|
| 403 |
+
CodeShell-7B,Chat Model,Chinese,Script,8.85
|
| 404 |
+
CodeShell-7B,Chat Model,Japanese,Script,22.39
|
| 405 |
+
CodeShell-7B,Chat Model,French,Script,20.52
|
| 406 |
+
CodeShell-7B,Chat Model,English,Compile,24.3
|
| 407 |
+
CodeShell-7B,Chat Model,Chinese,Compile,30.43
|
| 408 |
+
CodeShell-7B,Chat Model,Japanese,Compile,28.21
|
| 409 |
+
CodeShell-7B,Chat Model,French,Compile,24.55
|
| 410 |
+
CodeLlama-7b,Base Model,English,Interpreter,29.98
|
| 411 |
+
CodeLlama-7b,Base Model,Chinese,Interpreter,31.8
|
| 412 |
+
CodeLlama-7b,Base Model,Japanese,Interpreter,25.17
|
| 413 |
+
CodeLlama-7b,Base Model,French,Interpreter,11.94
|
| 414 |
+
CodeLlama-7b,Base Model,English,Script,25.6
|
| 415 |
+
CodeLlama-7b,Base Model,Chinese,Script,11.6
|
| 416 |
+
CodeLlama-7b,Base Model,Japanese,Script,30.36
|
| 417 |
+
CodeLlama-7b,Base Model,French,Script,18.04
|
| 418 |
+
CodeLlama-7b,Base Model,English,Compile,25.52
|
| 419 |
+
CodeLlama-7b,Base Model,Chinese,Compile,29.2
|
| 420 |
+
CodeLlama-7b,Base Model,Japanese,Compile,27.23
|
| 421 |
+
CodeLlama-7b,Base Model,French,Compile,25.82
|
| 422 |
+
OctoCoder-15B,Chat Model,English,Interpreter,45.3
|
| 423 |
+
OctoCoder-15B,Chat Model,Chinese,Interpreter,32.8
|
| 424 |
+
OctoCoder-15B,Chat Model,Japanese,Interpreter,26.76
|
| 425 |
+
OctoCoder-15B,Chat Model,French,Interpreter,10.61
|
| 426 |
+
OctoCoder-15B,Chat Model,English,Script,24.5
|
| 427 |
+
OctoCoder-15B,Chat Model,Chinese,Script,13.35
|
| 428 |
+
OctoCoder-15B,Chat Model,Japanese,Script,22.56
|
| 429 |
+
OctoCoder-15B,Chat Model,French,Script,14.39
|
| 430 |
+
OctoCoder-15B,Chat Model,English,Compile,18.24
|
| 431 |
+
OctoCoder-15B,Chat Model,Chinese,Compile,26.03
|
| 432 |
+
OctoCoder-15B,Chat Model,Japanese,Compile,29.32
|
| 433 |
+
OctoCoder-15B,Chat Model,French,Compile,24.26
|
| 434 |
+
CodeLlama-7b-Python,Base Model,English,Interpreter,40.48
|
| 435 |
+
CodeLlama-7b-Python,Base Model,Chinese,Interpreter,36.34
|
| 436 |
+
CodeLlama-7b-Python,Base Model,Japanese,Interpreter,1.08
|
| 437 |
+
CodeLlama-7b-Python,Base Model,French,Interpreter,9.04
|
| 438 |
+
CodeLlama-7b-Python,Base Model,English,Script,28.53
|
| 439 |
+
CodeLlama-7b-Python,Base Model,Chinese,Script,8.94
|
| 440 |
+
CodeLlama-7b-Python,Base Model,Japanese,Script,26.15
|
| 441 |
+
CodeLlama-7b-Python,Base Model,French,Script,18.25
|
| 442 |
+
CodeLlama-7b-Python,Base Model,English,Compile,26.75
|
| 443 |
+
CodeLlama-7b-Python,Base Model,Chinese,Compile,29.15
|
| 444 |
+
CodeLlama-7b-Python,Base Model,Japanese,Compile,30.34
|
| 445 |
+
CodeLlama-7b-Python,Base Model,French,Compile,26.96
|
| 446 |
+
StarCoder-15B,Base Model,English,Interpreter,33.57
|
| 447 |
+
StarCoder-15B,Base Model,Chinese,Interpreter,30.79
|
| 448 |
+
StarCoder-15B,Base Model,Japanese,Interpreter,26.08
|
| 449 |
+
StarCoder-15B,Base Model,French,Interpreter,0.07
|
| 450 |
+
StarCoder-15B,Base Model,English,Script,23.02
|
| 451 |
+
StarCoder-15B,Base Model,Chinese,Script,13.57
|
| 452 |
+
StarCoder-15B,Base Model,Japanese,Script,23.89
|
| 453 |
+
StarCoder-15B,Base Model,French,Script,15.5
|
| 454 |
+
StarCoder-15B,Base Model,English,Compile,22.74
|
| 455 |
+
StarCoder-15B,Base Model,Chinese,Compile,30.22
|
| 456 |
+
StarCoder-15B,Base Model,Japanese,Compile,31.55
|
| 457 |
+
StarCoder-15B,Base Model,French,Compile,21.84
|
| 458 |
+
Falcon-180B,Base Model,English,Interpreter,35.37
|
| 459 |
+
Falcon-180B,Base Model,Chinese,Interpreter,31.68
|
| 460 |
+
Falcon-180B,Base Model,Japanese,Interpreter,
|
| 461 |
+
Falcon-180B,Base Model,French,Interpreter,10.56
|
| 462 |
+
Falcon-180B,Base Model,English,Script,24.53
|
| 463 |
+
Falcon-180B,Base Model,Chinese,Script,14.1
|
| 464 |
+
Falcon-180B,Base Model,Japanese,Script,26.71
|
| 465 |
+
Falcon-180B,Base Model,French,Script,
|
| 466 |
+
Falcon-180B,Base Model,English,Compile,15.82
|
| 467 |
+
Falcon-180B,Base Model,Chinese,Compile,28.48
|
| 468 |
+
Falcon-180B,Base Model,Japanese,Compile,28.57
|
| 469 |
+
Falcon-180B,Base Model,French,Compile,25.0
|
| 470 |
+
StarCoderBase-15B,Base Model,English,Interpreter,30.35
|
| 471 |
+
StarCoderBase-15B,Base Model,Chinese,Interpreter,31.7
|
| 472 |
+
StarCoderBase-15B,Base Model,Japanese,Interpreter,26.75
|
| 473 |
+
StarCoderBase-15B,Base Model,French,Interpreter,11.77
|
| 474 |
+
StarCoderBase-15B,Base Model,English,Script,21.09
|
| 475 |
+
StarCoderBase-15B,Base Model,Chinese,Script,10.01
|
| 476 |
+
StarCoderBase-15B,Base Model,Japanese,Script,26.61
|
| 477 |
+
StarCoderBase-15B,Base Model,French,Script,10.18
|
| 478 |
+
StarCoderBase-15B,Base Model,English,Compile,16.74
|
| 479 |
+
StarCoderBase-15B,Base Model,Chinese,Compile,28.53
|
| 480 |
+
StarCoderBase-15B,Base Model,Japanese,Compile,30.56
|
| 481 |
+
StarCoderBase-15B,Base Model,French,Compile,24.46
|
| 482 |
+
StarCoder2-3B,Base Model,English,Interpreter,31.44
|
| 483 |
+
StarCoder2-3B,Base Model,Chinese,Interpreter,35.37
|
| 484 |
+
StarCoder2-3B,Base Model,Japanese,Interpreter,27.61
|
| 485 |
+
StarCoder2-3B,Base Model,French,Interpreter,7.8
|
| 486 |
+
StarCoder2-3B,Base Model,English,Script,19.87
|
| 487 |
+
StarCoder2-3B,Base Model,Chinese,Script,12.56
|
| 488 |
+
StarCoder2-3B,Base Model,Japanese,Script,28.01
|
| 489 |
+
StarCoder2-3B,Base Model,French,Script,14.22
|
| 490 |
+
StarCoder2-3B,Base Model,English,Compile,25.09
|
| 491 |
+
StarCoder2-3B,Base Model,Chinese,Compile,27.41
|
| 492 |
+
StarCoder2-3B,Base Model,Japanese,Compile,27.24
|
| 493 |
+
StarCoder2-3B,Base Model,French,Compile,24.52
|
| 494 |
+
CodeGeex2-6B,Base Model,English,Interpreter,33.49
|
| 495 |
+
CodeGeex2-6B,Base Model,Chinese,Interpreter,29.9
|
| 496 |
+
CodeGeex2-6B,Base Model,Japanese,Interpreter,25.27
|
| 497 |
+
CodeGeex2-6B,Base Model,French,Interpreter,11.75
|
| 498 |
+
CodeGeex2-6B,Base Model,English,Script,20.93
|
| 499 |
+
CodeGeex2-6B,Base Model,Chinese,Script,8.44
|
| 500 |
+
CodeGeex2-6B,Base Model,Japanese,Script,15.94
|
| 501 |
+
CodeGeex2-6B,Base Model,French,Script,14.58
|
| 502 |
+
CodeGeex2-6B,Base Model,English,Compile,22.06
|
| 503 |
+
CodeGeex2-6B,Base Model,Chinese,Compile,23.46
|
| 504 |
+
CodeGeex2-6B,Base Model,Japanese,Compile,28.45
|
| 505 |
+
CodeGeex2-6B,Base Model,French,Compile,20.45
|
| 506 |
+
StarCoderBase-7B,Base Model,English,Interpreter,28.37
|
| 507 |
+
StarCoderBase-7B,Base Model,Chinese,Interpreter,27.35
|
| 508 |
+
StarCoderBase-7B,Base Model,Japanese,Interpreter,22.12
|
| 509 |
+
StarCoderBase-7B,Base Model,French,Interpreter,11.08
|
| 510 |
+
StarCoderBase-7B,Base Model,English,Script,21.77
|
| 511 |
+
StarCoderBase-7B,Base Model,Chinese,Script,8.1
|
| 512 |
+
StarCoderBase-7B,Base Model,Japanese,Script,23.35
|
| 513 |
+
StarCoderBase-7B,Base Model,French,Script,14.51
|
| 514 |
+
StarCoderBase-7B,Base Model,English,Compile,15.1
|
| 515 |
+
StarCoderBase-7B,Base Model,Chinese,Compile,24.44
|
| 516 |
+
StarCoderBase-7B,Base Model,Japanese,Compile,23.3
|
| 517 |
+
StarCoderBase-7B,Base Model,French,Compile,22.6
|
| 518 |
+
OctoGeeX-7B,Chat Model,English,Interpreter,42.28
|
| 519 |
+
OctoGeeX-7B,Chat Model,Chinese,Interpreter,28.5
|
| 520 |
+
OctoGeeX-7B,Chat Model,Japanese,Interpreter,25.85
|
| 521 |
+
OctoGeeX-7B,Chat Model,French,Interpreter,12.02
|
| 522 |
+
OctoGeeX-7B,Chat Model,English,Script,22.94
|
| 523 |
+
OctoGeeX-7B,Chat Model,Chinese,Script,9.77
|
| 524 |
+
OctoGeeX-7B,Chat Model,Japanese,Script,16.19
|
| 525 |
+
OctoGeeX-7B,Chat Model,French,Script,13.66
|
| 526 |
+
OctoGeeX-7B,Chat Model,English,Compile,17.03
|
| 527 |
+
OctoGeeX-7B,Chat Model,Chinese,Compile,19.33
|
| 528 |
+
OctoGeeX-7B,Chat Model,Japanese,Compile,23.93
|
| 529 |
+
OctoGeeX-7B,Chat Model,French,Compile,17.94
|
| 530 |
+
WizardCoder-3B-V1.0,Chat Model,English,Interpreter,32.92
|
| 531 |
+
WizardCoder-3B-V1.0,Chat Model,Chinese,Interpreter,26.16
|
| 532 |
+
WizardCoder-3B-V1.0,Chat Model,Japanese,Interpreter,24.83
|
| 533 |
+
WizardCoder-3B-V1.0,Chat Model,French,Interpreter,9.44
|
| 534 |
+
WizardCoder-3B-V1.0,Chat Model,English,Script,19.6
|
| 535 |
+
WizardCoder-3B-V1.0,Chat Model,Chinese,Script,7.91
|
| 536 |
+
WizardCoder-3B-V1.0,Chat Model,Japanese,Script,21.75
|
| 537 |
+
WizardCoder-3B-V1.0,Chat Model,French,Script,13.64
|
| 538 |
+
WizardCoder-3B-V1.0,Chat Model,English,Compile,15.7
|
| 539 |
+
WizardCoder-3B-V1.0,Chat Model,Chinese,Compile,24.34
|
| 540 |
+
WizardCoder-3B-V1.0,Chat Model,Japanese,Compile,24.94
|
| 541 |
+
WizardCoder-3B-V1.0,Chat Model,French,Compile,20.56
|
| 542 |
+
CodeGen25-7B-multi,Base Model,English,Interpreter,28.7
|
| 543 |
+
CodeGen25-7B-multi,Base Model,Chinese,Interpreter,26.27
|
| 544 |
+
CodeGen25-7B-multi,Base Model,Japanese,Interpreter,21.98
|
| 545 |
+
CodeGen25-7B-multi,Base Model,French,Interpreter,10.37
|
| 546 |
+
CodeGen25-7B-multi,Base Model,English,Script,19.11
|
| 547 |
+
CodeGen25-7B-multi,Base Model,Chinese,Script,8.84
|
| 548 |
+
CodeGen25-7B-multi,Base Model,Japanese,Script,23.44
|
| 549 |
+
CodeGen25-7B-multi,Base Model,French,Script,11.59
|
| 550 |
+
CodeGen25-7B-multi,Base Model,English,Compile,16.62
|
| 551 |
+
CodeGen25-7B-multi,Base Model,Chinese,Compile,26.01
|
| 552 |
+
CodeGen25-7B-multi,Base Model,Japanese,Compile,25.75
|
| 553 |
+
CodeGen25-7B-multi,Base Model,French,Compile,21.84
|
| 554 |
+
CodeGemma-2B,Base Model,English,Interpreter,27.28
|
| 555 |
+
CodeGemma-2B,Base Model,Chinese,Interpreter,29.94
|
| 556 |
+
CodeGemma-2B,Base Model,Japanese,Interpreter,28.76
|
| 557 |
+
CodeGemma-2B,Base Model,French,Interpreter,8.77
|
| 558 |
+
CodeGemma-2B,Base Model,English,Script,0.01
|
| 559 |
+
CodeGemma-2B,Base Model,Chinese,Script,9.54
|
| 560 |
+
CodeGemma-2B,Base Model,Japanese,Script,25.23
|
| 561 |
+
CodeGemma-2B,Base Model,French,Script,10.71
|
| 562 |
+
CodeGemma-2B,Base Model,English,Compile,6.3
|
| 563 |
+
CodeGemma-2B,Base Model,Chinese,Compile,24.71
|
| 564 |
+
CodeGemma-2B,Base Model,Japanese,Compile,29.33
|
| 565 |
+
CodeGemma-2B,Base Model,French,Compile,26.81
|
| 566 |
+
Refact-1.6B,Chat Model,English,Interpreter,31.1
|
| 567 |
+
Refact-1.6B,Chat Model,Chinese,Interpreter,22.36
|
| 568 |
+
Refact-1.6B,Chat Model,Japanese,Interpreter,22.36
|
| 569 |
+
Refact-1.6B,Chat Model,French,Interpreter,4.97
|
| 570 |
+
Refact-1.6B,Chat Model,English,Script,13.84
|
| 571 |
+
Refact-1.6B,Chat Model,Chinese,Script,10.26
|
| 572 |
+
Refact-1.6B,Chat Model,Japanese,Script,15.53
|
| 573 |
+
Refact-1.6B,Chat Model,French,Script,13.04
|
| 574 |
+
Refact-1.6B,Chat Model,English,Compile,18.35
|
| 575 |
+
Refact-1.6B,Chat Model,Chinese,Compile,22.78
|
| 576 |
+
Refact-1.6B,Chat Model,Japanese,Compile,21.12
|
| 577 |
+
Refact-1.6B,Chat Model,French,Compile,18.59
|
| 578 |
+
Stable-code-3b,Base Model,English,Interpreter,30.72
|
| 579 |
+
Stable-code-3b,Base Model,Chinese,Interpreter,31.64
|
| 580 |
+
Stable-code-3b,Base Model,Japanese,Interpreter,23.68
|
| 581 |
+
Stable-code-3b,Base Model,French,Interpreter,0.0
|
| 582 |
+
Stable-code-3b,Base Model,English,Script,21.41
|
| 583 |
+
Stable-code-3b,Base Model,Chinese,Script,10.09
|
| 584 |
+
Stable-code-3b,Base Model,Japanese,Script,17.54
|
| 585 |
+
Stable-code-3b,Base Model,French,Script,13.37
|
| 586 |
+
Stable-code-3b,Base Model,English,Compile,0.0
|
| 587 |
+
Stable-code-3b,Base Model,Chinese,Compile,28.75
|
| 588 |
+
Stable-code-3b,Base Model,Japanese,Compile,29.42
|
| 589 |
+
Stable-code-3b,Base Model,French,Compile,22.15
|
| 590 |
+
DeepSeek-Coder-1b-base,Base Model,English,Interpreter,32.13
|
| 591 |
+
DeepSeek-Coder-1b-base,Base Model,Chinese,Interpreter,28.46
|
| 592 |
+
DeepSeek-Coder-1b-base,Base Model,Japanese,Interpreter,22.75
|
| 593 |
+
DeepSeek-Coder-1b-base,Base Model,French,Interpreter,9.58
|
| 594 |
+
DeepSeek-Coder-1b-base,Base Model,English,Script,15.17
|
| 595 |
+
DeepSeek-Coder-1b-base,Base Model,Chinese,Script,9.91
|
| 596 |
+
DeepSeek-Coder-1b-base,Base Model,Japanese,Script,19.44
|
| 597 |
+
DeepSeek-Coder-1b-base,Base Model,French,Script,11.4
|
| 598 |
+
DeepSeek-Coder-1b-base,Base Model,English,Compile,11.39
|
| 599 |
+
DeepSeek-Coder-1b-base,Base Model,Chinese,Compile,27.16
|
| 600 |
+
DeepSeek-Coder-1b-base,Base Model,Japanese,Compile,27.96
|
| 601 |
+
DeepSeek-Coder-1b-base,Base Model,French,Compile,18.13
|
| 602 |
+
StarCoderBase-3B,Base Model,English,Interpreter,21.5
|
| 603 |
+
StarCoderBase-3B,Base Model,Chinese,Interpreter,21.32
|
| 604 |
+
StarCoderBase-3B,Base Model,Japanese,Interpreter,18.55
|
| 605 |
+
StarCoderBase-3B,Base Model,French,Interpreter,7.87
|
| 606 |
+
StarCoderBase-3B,Base Model,English,Script,16.1
|
| 607 |
+
StarCoderBase-3B,Base Model,Chinese,Script,4.97
|
| 608 |
+
StarCoderBase-3B,Base Model,Japanese,Script,18.04
|
| 609 |
+
StarCoderBase-3B,Base Model,French,Script,10.1
|
| 610 |
+
StarCoderBase-3B,Base Model,English,Compile,9.98
|
| 611 |
+
StarCoderBase-3B,Base Model,Chinese,Compile,19.25
|
| 612 |
+
StarCoderBase-3B,Base Model,Japanese,Compile,19.43
|
| 613 |
+
StarCoderBase-3B,Base Model,French,Compile,16.32
|
| 614 |
+
WizardCoder-1B-V1.0,Chat Model,English,Interpreter,23.17
|
| 615 |
+
WizardCoder-1B-V1.0,Chat Model,Chinese,Interpreter,19.13
|
| 616 |
+
WizardCoder-1B-V1.0,Chat Model,Japanese,Interpreter,14.71
|
| 617 |
+
WizardCoder-1B-V1.0,Chat Model,French,Interpreter,6.51
|
| 618 |
+
WizardCoder-1B-V1.0,Chat Model,English,Script,13.85
|
| 619 |
+
WizardCoder-1B-V1.0,Chat Model,Chinese,Script,4.64
|
| 620 |
+
WizardCoder-1B-V1.0,Chat Model,Japanese,Script,15.52
|
| 621 |
+
WizardCoder-1B-V1.0,Chat Model,French,Script,10.01
|
| 622 |
+
WizardCoder-1B-V1.0,Chat Model,English,Compile,9.59
|
| 623 |
+
WizardCoder-1B-V1.0,Chat Model,Chinese,Compile,19.68
|
| 624 |
+
WizardCoder-1B-V1.0,Chat Model,Japanese,Compile,15.94
|
| 625 |
+
WizardCoder-1B-V1.0,Chat Model,French,Compile,13.91
|
| 626 |
+
Replit-2.7B,Base Model,English,Interpreter,20.12
|
| 627 |
+
Replit-2.7B,Base Model,Chinese,Interpreter,20.18
|
| 628 |
+
Replit-2.7B,Base Model,Japanese,Interpreter,16.14
|
| 629 |
+
Replit-2.7B,Base Model,French,Interpreter,3.22
|
| 630 |
+
Replit-2.7B,Base Model,English,Script,1.24
|
| 631 |
+
Replit-2.7B,Base Model,Chinese,Script,6.41
|
| 632 |
+
Replit-2.7B,Base Model,Japanese,Script,2.11
|
| 633 |
+
Replit-2.7B,Base Model,French,Script,7.2
|
| 634 |
+
Replit-2.7B,Base Model,English,Compile,5.88
|
| 635 |
+
Replit-2.7B,Base Model,Chinese,Compile,21.39
|
| 636 |
+
Replit-2.7B,Base Model,Japanese,Compile,20.37
|
| 637 |
+
Replit-2.7B,Base Model,French,Compile,15.19
|
| 638 |
+
CodeGen25-7B-mono,Base Model,English,Interpreter,33.08
|
| 639 |
+
CodeGen25-7B-mono,Base Model,Chinese,Interpreter,23.22
|
| 640 |
+
CodeGen25-7B-mono,Base Model,Japanese,Interpreter,16.75
|
| 641 |
+
CodeGen25-7B-mono,Base Model,French,Interpreter,4.07
|
| 642 |
+
CodeGen25-7B-mono,Base Model,English,Script,4.65
|
| 643 |
+
CodeGen25-7B-mono,Base Model,Chinese,Script,4.32
|
| 644 |
+
CodeGen25-7B-mono,Base Model,Japanese,Script,6.75
|
| 645 |
+
CodeGen25-7B-mono,Base Model,French,Script,4.41
|
| 646 |
+
CodeGen25-7B-mono,Base Model,English,Compile,1.71
|
| 647 |
+
CodeGen25-7B-mono,Base Model,Chinese,Compile,19.75
|
| 648 |
+
CodeGen25-7B-mono,Base Model,Japanese,Compile,18.62
|
| 649 |
+
CodeGen25-7B-mono,Base Model,French,Compile,7.83
|
| 650 |
+
StarCoderBase-1.1B,Base Model,English,Interpreter,15.17
|
| 651 |
+
StarCoderBase-1.1B,Base Model,Chinese,Interpreter,13.38
|
| 652 |
+
StarCoderBase-1.1B,Base Model,Japanese,Interpreter,9.94
|
| 653 |
+
StarCoderBase-1.1B,Base Model,French,Interpreter,5.03
|
| 654 |
+
StarCoderBase-1.1B,Base Model,English,Script,11.31
|
| 655 |
+
StarCoderBase-1.1B,Base Model,Chinese,Script,4.65
|
| 656 |
+
StarCoderBase-1.1B,Base Model,Japanese,Script,12.52
|
| 657 |
+
StarCoderBase-1.1B,Base Model,French,Script,5.73
|
| 658 |
+
StarCoderBase-1.1B,Base Model,English,Compile,3.92
|
| 659 |
+
StarCoderBase-1.1B,Base Model,Chinese,Compile,14.2
|
| 660 |
+
StarCoderBase-1.1B,Base Model,Japanese,Compile,11.68
|
| 661 |
+
StarCoderBase-1.1B,Base Model,French,Compile,10.24
|
| 662 |
+
CodeGen-16B-Multi,Base Model,English,Interpreter,19.26
|
| 663 |
+
CodeGen-16B-Multi,Base Model,Chinese,Interpreter,19.15
|
| 664 |
+
CodeGen-16B-Multi,Base Model,Japanese,Interpreter,8.37
|
| 665 |
+
CodeGen-16B-Multi,Base Model,French,Interpreter,0.66
|
| 666 |
+
CodeGen-16B-Multi,Base Model,English,Script,0.0
|
| 667 |
+
CodeGen-16B-Multi,Base Model,Chinese,Script,7.68
|
| 668 |
+
CodeGen-16B-Multi,Base Model,Japanese,Script,8.5
|
| 669 |
+
CodeGen-16B-Multi,Base Model,French,Script,6.45
|
| 670 |
+
CodeGen-16B-Multi,Base Model,English,Compile,1.25
|
| 671 |
+
CodeGen-16B-Multi,Base Model,Chinese,Compile,22.2
|
| 672 |
+
CodeGen-16B-Multi,Base Model,Japanese,Compile,21.0
|
| 673 |
+
CodeGen-16B-Multi,Base Model,French,Compile,4.21
|
| 674 |
+
StableCode-3B-alpha,Base Model,English,Interpreter,20.2
|
| 675 |
+
StableCode-3B-alpha,Base Model,Chinese,Interpreter,18.98
|
| 676 |
+
StableCode-3B-alpha,Base Model,Japanese,Interpreter,3.95
|
| 677 |
+
StableCode-3B-alpha,Base Model,French,Interpreter,0.008
|
| 678 |
+
StableCode-3B-alpha,Base Model,English,Script,0.0
|
| 679 |
+
StableCode-3B-alpha,Base Model,Chinese,Script,4.77
|
| 680 |
+
StableCode-3B-alpha,Base Model,Japanese,Script,5.14
|
| 681 |
+
StableCode-3B-alpha,Base Model,French,Script,0.8
|
| 682 |
+
StableCode-3B-alpha,Base Model,English,Compile,0.98
|
| 683 |
+
StableCode-3B-alpha,Base Model,Chinese,Compile,19.54
|
| 684 |
+
StableCode-3B-alpha,Base Model,Japanese,Compile,20.77
|
| 685 |
+
StableCode-3B-alpha,Base Model,French,Compile,2.03
|
| 686 |
+
DeciCoder-1B,Base Model,English,Interpreter,19.32
|
| 687 |
+
DeciCoder-1B,Base Model,Chinese,Interpreter,17.85
|
| 688 |
+
DeciCoder-1B,Base Model,Japanese,Interpreter,2.01
|
| 689 |
+
DeciCoder-1B,Base Model,French,Interpreter,0.47
|
| 690 |
+
DeciCoder-1B,Base Model,English,Script,0.0
|
| 691 |
+
DeciCoder-1B,Base Model,Chinese,Script,6.08
|
| 692 |
+
DeciCoder-1B,Base Model,Japanese,Script,0.0
|
| 693 |
+
DeciCoder-1B,Base Model,French,Script,0.1
|
| 694 |
+
DeciCoder-1B,Base Model,English,Compile,0.63
|
| 695 |
+
DeciCoder-1B,Base Model,Chinese,Compile,15.3
|
| 696 |
+
DeciCoder-1B,Base Model,Japanese,Compile,6.87
|
| 697 |
+
DeciCoder-1B,Base Model,French,Compile,1.72
|
| 698 |
+
Phi-1,Base Model,English,Interpreter,51.22
|
| 699 |
+
Phi-1,Base Model,Chinese,Interpreter,19.25
|
| 700 |
+
Phi-1,Base Model,Japanese,Interpreter,12.42
|
| 701 |
+
Phi-1,Base Model,French,Interpreter,3.11
|
| 702 |
+
Phi-1,Base Model,English,Script,0.63
|
| 703 |
+
Phi-1,Base Model,Chinese,Script,7.05
|
| 704 |
+
Phi-1,Base Model,Japanese,Script,6.21
|
| 705 |
+
Phi-1,Base Model,French,Script,6.21
|
| 706 |
+
Phi-1,Base Model,English,Compile,10.13
|
| 707 |
+
Phi-1,Base Model,Chinese,Compile,10.76
|
| 708 |
+
Phi-1,Base Model,Japanese,Compile,14.29
|
| 709 |
+
Phi-1,Base Model,French,Compile,4.49
|
| 710 |
+
SantaCoder-1.1B,Base Model,English,Interpreter,18.12
|
| 711 |
+
SantaCoder-1.1B,Base Model,Chinese,Interpreter,15.47
|
| 712 |
+
SantaCoder-1.1B,Base Model,Japanese,Interpreter,1.5
|
| 713 |
+
SantaCoder-1.1B,Base Model,French,Interpreter,0.0
|
| 714 |
+
SantaCoder-1.1B,Base Model,English,Script,0.0
|
| 715 |
+
SantaCoder-1.1B,Base Model,Chinese,Script,0.0
|
| 716 |
+
SantaCoder-1.1B,Base Model,Japanese,Script,0.1
|
| 717 |
+
SantaCoder-1.1B,Base Model,French,Script,0.0
|
| 718 |
+
SantaCoder-1.1B,Base Model,English,Compile,0.7
|
| 719 |
+
SantaCoder-1.1B,Base Model,Chinese,Compile,15.0
|
| 720 |
+
SantaCoder-1.1B,Base Model,Japanese,Compile,6.2
|
| 721 |
+
SantaCoder-1.1B,Base Model,French,Compile,2.0
|