Update space
Browse files
app.py
CHANGED
|
@@ -164,25 +164,58 @@ with demo:
|
|
| 164 |
"""
|
| 165 |
gr.Markdown(DESCRIPTION_TEXT, elem_classes="markdown-text")
|
| 166 |
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
|
|
|
|
|
|
| 183 |
)
|
| 184 |
-
)
|
| 185 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 186 |
|
| 187 |
|
| 188 |
with gr.TabItem("🔢 Math", elem_id="math-tab-table", id=2):
|
|
|
|
| 164 |
"""
|
| 165 |
gr.Markdown(DESCRIPTION_TEXT, elem_classes="markdown-text")
|
| 166 |
|
| 167 |
+
with gr.TabItem("Sort by Rank", elem_id="overall_sort_by_rank_subtab", id=0, elem_classes="subtab"):
|
| 168 |
+
leaderboard = overall_leaderboard(
|
| 169 |
+
get_model_leaderboard_df(
|
| 170 |
+
model_result_path,
|
| 171 |
+
benchmark_cols=[
|
| 172 |
+
# AutoEvalColumn.rank_overall.name,
|
| 173 |
+
AutoEvalColumn.model.name,
|
| 174 |
+
AutoEvalColumn.rank_overall.name,
|
| 175 |
+
AutoEvalColumn.rank_math_algebra.name,
|
| 176 |
+
AutoEvalColumn.rank_math_geometry.name,
|
| 177 |
+
AutoEvalColumn.rank_math_probability.name,
|
| 178 |
+
AutoEvalColumn.rank_reason_logical.name,
|
| 179 |
+
AutoEvalColumn.rank_reason_social.name,
|
| 180 |
+
AutoEvalColumn.rank_chemistry.name,
|
| 181 |
+
# AutoEvalColumn.rank_cpp.name,
|
| 182 |
+
],
|
| 183 |
+
rank_col=[],
|
| 184 |
+
)
|
| 185 |
)
|
|
|
|
| 186 |
|
| 187 |
+
with gr.TabItem("Sort by Score", elem_id="overall_sort_by_score_subtab", id=1, elem_classes="subtab"):
|
| 188 |
+
leaderboard = overall_leaderboard(
|
| 189 |
+
get_model_leaderboard_df(
|
| 190 |
+
model_result_path,
|
| 191 |
+
benchmark_cols=[
|
| 192 |
+
# AutoEvalColumn.rank_overall.name,
|
| 193 |
+
AutoEvalColumn.model.name,
|
| 194 |
+
AutoEvalColumn.license.name,
|
| 195 |
+
AutoEvalColumn.organization.name,
|
| 196 |
+
AutoEvalColumn.knowledge_cutoff.name,
|
| 197 |
+
|
| 198 |
+
AutoEvalColumn.score_overall.name,
|
| 199 |
+
AutoEvalColumn.score_math_algebra.name,
|
| 200 |
+
AutoEvalColumn.score_math_geometry.name,
|
| 201 |
+
AutoEvalColumn.score_math_probability.name,
|
| 202 |
+
AutoEvalColumn.score_reason_logical.name,
|
| 203 |
+
AutoEvalColumn.score_reason_social.name,
|
| 204 |
+
AutoEvalColumn.score_chemistry.name,
|
| 205 |
+
# AutoEvalColumn.score_cpp.name,
|
| 206 |
+
|
| 207 |
+
# AutoEvalColumn.rank_overall.name,
|
| 208 |
+
# AutoEvalColumn.rank_math_algebra.name,
|
| 209 |
+
# AutoEvalColumn.rank_math_geometry.name,
|
| 210 |
+
# AutoEvalColumn.rank_math_probability.name,
|
| 211 |
+
# AutoEvalColumn.rank_reason_logical.name,
|
| 212 |
+
# AutoEvalColumn.rank_reason_social.name,
|
| 213 |
+
# AutoEvalColumn.rank_chemistry.name,
|
| 214 |
+
# AutoEvalColumn.rank_cpp.name,
|
| 215 |
+
],
|
| 216 |
+
rank_col=['sort_by_score'],
|
| 217 |
+
)
|
| 218 |
+
)
|
| 219 |
|
| 220 |
|
| 221 |
with gr.TabItem("🔢 Math", elem_id="math-tab-table", id=2):
|