ZachW commited on
Commit
acacd48
·
verified ·
1 Parent(s): c31b45c

Upload extrapolation artifact: 050302 OPD Ref-KL step20 graph aggregate results

Browse files
050302/evals/opd_refkl_sweep/step20/graph_results/results.json ADDED
@@ -0,0 +1,1780 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "opd050302_refkl_s020_merged_hf_id_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "crazy_zootopia": {
6
+ "per_op_pass_at_k": {
7
+ "2": {
8
+ "pass@1": 0.9376947040498442,
9
+ "pass@2": 0.9688473520249221,
10
+ "pass@4": 0.9781931464174455,
11
+ "pass@8": 0.9844236760124611,
12
+ "pass@16": 0.9875389408099688,
13
+ "pass@32": 0.9906542056074766,
14
+ "pass@64": 0.9906542056074766,
15
+ "pass@128": 0.9937694704049844
16
+ },
17
+ "3": {
18
+ "pass@1": 0.9174311926605505,
19
+ "pass@2": 0.9418960244648318,
20
+ "pass@4": 0.944954128440367,
21
+ "pass@8": 0.9541284403669725,
22
+ "pass@16": 0.9602446483180428,
23
+ "pass@32": 0.963302752293578,
24
+ "pass@64": 0.9785932721712538,
25
+ "pass@128": 0.9785932721712538
26
+ },
27
+ "4": {
28
+ "pass@1": 0.68125,
29
+ "pass@2": 0.70625,
30
+ "pass@4": 0.71875,
31
+ "pass@8": 0.728125,
32
+ "pass@16": 0.74375,
33
+ "pass@32": 0.765625,
34
+ "pass@64": 0.778125,
35
+ "pass@128": 0.796875
36
+ },
37
+ "5": {
38
+ "pass@1": 0.580952380952381,
39
+ "pass@2": 0.6063492063492063,
40
+ "pass@4": 0.6190476190476191,
41
+ "pass@8": 0.6476190476190476,
42
+ "pass@16": 0.6666666666666666,
43
+ "pass@32": 0.6857142857142857,
44
+ "pass@64": 0.6984126984126984,
45
+ "pass@128": 0.7142857142857143
46
+ },
47
+ "6": {
48
+ "pass@1": 0.5089820359281437,
49
+ "pass@2": 0.5658682634730539,
50
+ "pass@4": 0.6077844311377245,
51
+ "pass@8": 0.6437125748502994,
52
+ "pass@16": 0.6676646706586826,
53
+ "pass@32": 0.6946107784431138,
54
+ "pass@64": 0.7125748502994012,
55
+ "pass@128": 0.7275449101796407
56
+ },
57
+ "7": {
58
+ "pass@1": 0.4822485207100592,
59
+ "pass@2": 0.5266272189349113,
60
+ "pass@4": 0.5562130177514792,
61
+ "pass@8": 0.5710059171597633,
62
+ "pass@16": 0.5976331360946746,
63
+ "pass@32": 0.621301775147929,
64
+ "pass@64": 0.636094674556213,
65
+ "pass@128": 0.6538461538461539
66
+ },
67
+ "8": {
68
+ "pass@1": 0.4519230769230769,
69
+ "pass@2": 0.4807692307692308,
70
+ "pass@4": 0.5064102564102564,
71
+ "pass@8": 0.5160256410256411,
72
+ "pass@16": 0.5416666666666666,
73
+ "pass@32": 0.5608974358974359,
74
+ "pass@64": 0.5737179487179487,
75
+ "pass@128": 0.592948717948718
76
+ },
77
+ "9": {
78
+ "pass@1": 0.43380281690140843,
79
+ "pass@2": 0.4647887323943662,
80
+ "pass@4": 0.504225352112676,
81
+ "pass@8": 0.5352112676056338,
82
+ "pass@16": 0.5633802816901409,
83
+ "pass@32": 0.5746478873239437,
84
+ "pass@64": 0.5943661971830986,
85
+ "pass@128": 0.6
86
+ },
87
+ "10": {
88
+ "pass@1": 0.471976401179941,
89
+ "pass@2": 0.49557522123893805,
90
+ "pass@4": 0.5132743362831859,
91
+ "pass@8": 0.5191740412979351,
92
+ "pass@16": 0.5309734513274337,
93
+ "pass@32": 0.5309734513274337,
94
+ "pass@64": 0.5368731563421829,
95
+ "pass@128": 0.5486725663716814
96
+ }
97
+ },
98
+ "per_op_pass_at_columns": {
99
+ "pass@1": {
100
+ "2": 0.9376947040498442,
101
+ "3": 0.9174311926605505,
102
+ "4": 0.68125,
103
+ "5": 0.580952380952381,
104
+ "6": 0.5089820359281437,
105
+ "7": 0.4822485207100592,
106
+ "8": 0.4519230769230769,
107
+ "9": 0.43380281690140843,
108
+ "10": 0.471976401179941
109
+ },
110
+ "pass@2": {
111
+ "2": 0.9688473520249221,
112
+ "3": 0.9418960244648318,
113
+ "4": 0.70625,
114
+ "5": 0.6063492063492063,
115
+ "6": 0.5658682634730539,
116
+ "7": 0.5266272189349113,
117
+ "8": 0.4807692307692308,
118
+ "9": 0.4647887323943662,
119
+ "10": 0.49557522123893805
120
+ },
121
+ "pass@4": {
122
+ "2": 0.9781931464174455,
123
+ "3": 0.944954128440367,
124
+ "4": 0.71875,
125
+ "5": 0.6190476190476191,
126
+ "6": 0.6077844311377245,
127
+ "7": 0.5562130177514792,
128
+ "8": 0.5064102564102564,
129
+ "9": 0.504225352112676,
130
+ "10": 0.5132743362831859
131
+ },
132
+ "pass@8": {
133
+ "2": 0.9844236760124611,
134
+ "3": 0.9541284403669725,
135
+ "4": 0.728125,
136
+ "5": 0.6476190476190476,
137
+ "6": 0.6437125748502994,
138
+ "7": 0.5710059171597633,
139
+ "8": 0.5160256410256411,
140
+ "9": 0.5352112676056338,
141
+ "10": 0.5191740412979351
142
+ },
143
+ "pass@16": {
144
+ "2": 0.9875389408099688,
145
+ "3": 0.9602446483180428,
146
+ "4": 0.74375,
147
+ "5": 0.6666666666666666,
148
+ "6": 0.6676646706586826,
149
+ "7": 0.5976331360946746,
150
+ "8": 0.5416666666666666,
151
+ "9": 0.5633802816901409,
152
+ "10": 0.5309734513274337
153
+ },
154
+ "pass@32": {
155
+ "2": 0.9906542056074766,
156
+ "3": 0.963302752293578,
157
+ "4": 0.765625,
158
+ "5": 0.6857142857142857,
159
+ "6": 0.6946107784431138,
160
+ "7": 0.621301775147929,
161
+ "8": 0.5608974358974359,
162
+ "9": 0.5746478873239437,
163
+ "10": 0.5309734513274337
164
+ },
165
+ "pass@64": {
166
+ "2": 0.9906542056074766,
167
+ "3": 0.9785932721712538,
168
+ "4": 0.778125,
169
+ "5": 0.6984126984126984,
170
+ "6": 0.7125748502994012,
171
+ "7": 0.636094674556213,
172
+ "8": 0.5737179487179487,
173
+ "9": 0.5943661971830986,
174
+ "10": 0.5368731563421829
175
+ },
176
+ "pass@128": {
177
+ "2": 0.9937694704049844,
178
+ "3": 0.9785932721712538,
179
+ "4": 0.796875,
180
+ "5": 0.7142857142857143,
181
+ "6": 0.7275449101796407,
182
+ "7": 0.6538461538461539,
183
+ "8": 0.592948717948718,
184
+ "9": 0.6,
185
+ "10": 0.5486725663716814
186
+ }
187
+ },
188
+ "total_pass_at_k": {
189
+ "pass@1": 0.6045254981425194,
190
+ "pass@2": 0.6369469773725093,
191
+ "pass@4": 0.6585612968591692,
192
+ "pass@8": 0.6754474839581223,
193
+ "pass@16": 0.6933468422830125,
194
+ "pass@32": 0.707531239446133,
195
+ "pass@64": 0.7200270178993583,
196
+ "pass@128": 0.7318473488686255
197
+ }
198
+ },
199
+ "movie_festival_awards": {
200
+ "per_op_pass_at_k": {
201
+ "2": {
202
+ "pass@1": 0.94,
203
+ "pass@2": 0.9742857142857143,
204
+ "pass@4": 0.9828571428571429,
205
+ "pass@8": 0.9857142857142858,
206
+ "pass@16": 0.9885714285714285,
207
+ "pass@32": 0.9942857142857143,
208
+ "pass@64": 0.9971428571428571,
209
+ "pass@128": 0.9971428571428571
210
+ },
211
+ "3": {
212
+ "pass@1": 0.9037900874635568,
213
+ "pass@2": 0.9329446064139941,
214
+ "pass@4": 0.9475218658892128,
215
+ "pass@8": 0.9591836734693877,
216
+ "pass@16": 0.9708454810495627,
217
+ "pass@32": 0.9737609329446064,
218
+ "pass@64": 0.9795918367346939,
219
+ "pass@128": 0.9825072886297376
220
+ },
221
+ "4": {
222
+ "pass@1": 0.6842105263157895,
223
+ "pass@2": 0.7076023391812866,
224
+ "pass@4": 0.7456140350877193,
225
+ "pass@8": 0.7631578947368421,
226
+ "pass@16": 0.7777777777777778,
227
+ "pass@32": 0.7894736842105263,
228
+ "pass@64": 0.8157894736842105,
229
+ "pass@128": 0.8362573099415205
230
+ },
231
+ "5": {
232
+ "pass@1": 0.5235294117647059,
233
+ "pass@2": 0.55,
234
+ "pass@4": 0.5911764705882353,
235
+ "pass@8": 0.6205882352941177,
236
+ "pass@16": 0.6529411764705882,
237
+ "pass@32": 0.6764705882352942,
238
+ "pass@64": 0.6911764705882353,
239
+ "pass@128": 0.6941176470588235
240
+ },
241
+ "6": {
242
+ "pass@1": 0.5205047318611987,
243
+ "pass@2": 0.555205047318612,
244
+ "pass@4": 0.5741324921135647,
245
+ "pass@8": 0.6214511041009464,
246
+ "pass@16": 0.6403785488958991,
247
+ "pass@32": 0.6624605678233438,
248
+ "pass@64": 0.6845425867507886,
249
+ "pass@128": 0.6908517350157729
250
+ },
251
+ "7": {
252
+ "pass@1": 0.4272151898734177,
253
+ "pass@2": 0.4620253164556962,
254
+ "pass@4": 0.4873417721518987,
255
+ "pass@8": 0.49683544303797467,
256
+ "pass@16": 0.5253164556962026,
257
+ "pass@32": 0.5474683544303798,
258
+ "pass@64": 0.569620253164557,
259
+ "pass@128": 0.5886075949367089
260
+ },
261
+ "8": {
262
+ "pass@1": 0.43843843843843844,
263
+ "pass@2": 0.4594594594594595,
264
+ "pass@4": 0.4804804804804805,
265
+ "pass@8": 0.5045045045045045,
266
+ "pass@16": 0.5255255255255256,
267
+ "pass@32": 0.5435435435435435,
268
+ "pass@64": 0.5615615615615616,
269
+ "pass@128": 0.5855855855855856
270
+ },
271
+ "9": {
272
+ "pass@1": 0.43729903536977494,
273
+ "pass@2": 0.4855305466237942,
274
+ "pass@4": 0.5144694533762058,
275
+ "pass@8": 0.5369774919614148,
276
+ "pass@16": 0.5594855305466238,
277
+ "pass@32": 0.5787781350482315,
278
+ "pass@64": 0.5852090032154341,
279
+ "pass@128": 0.6012861736334405
280
+ },
281
+ "10": {
282
+ "pass@1": 0.41492537313432837,
283
+ "pass@2": 0.44477611940298506,
284
+ "pass@4": 0.45671641791044776,
285
+ "pass@8": 0.4716417910447761,
286
+ "pass@16": 0.4925373134328358,
287
+ "pass@32": 0.49850746268656715,
288
+ "pass@64": 0.5074626865671642,
289
+ "pass@128": 0.5223880597014925
290
+ }
291
+ },
292
+ "per_op_pass_at_columns": {
293
+ "pass@1": {
294
+ "2": 0.94,
295
+ "3": 0.9037900874635568,
296
+ "4": 0.6842105263157895,
297
+ "5": 0.5235294117647059,
298
+ "6": 0.5205047318611987,
299
+ "7": 0.4272151898734177,
300
+ "8": 0.43843843843843844,
301
+ "9": 0.43729903536977494,
302
+ "10": 0.41492537313432837
303
+ },
304
+ "pass@2": {
305
+ "2": 0.9742857142857143,
306
+ "3": 0.9329446064139941,
307
+ "4": 0.7076023391812866,
308
+ "5": 0.55,
309
+ "6": 0.555205047318612,
310
+ "7": 0.4620253164556962,
311
+ "8": 0.4594594594594595,
312
+ "9": 0.4855305466237942,
313
+ "10": 0.44477611940298506
314
+ },
315
+ "pass@4": {
316
+ "2": 0.9828571428571429,
317
+ "3": 0.9475218658892128,
318
+ "4": 0.7456140350877193,
319
+ "5": 0.5911764705882353,
320
+ "6": 0.5741324921135647,
321
+ "7": 0.4873417721518987,
322
+ "8": 0.4804804804804805,
323
+ "9": 0.5144694533762058,
324
+ "10": 0.45671641791044776
325
+ },
326
+ "pass@8": {
327
+ "2": 0.9857142857142858,
328
+ "3": 0.9591836734693877,
329
+ "4": 0.7631578947368421,
330
+ "5": 0.6205882352941177,
331
+ "6": 0.6214511041009464,
332
+ "7": 0.49683544303797467,
333
+ "8": 0.5045045045045045,
334
+ "9": 0.5369774919614148,
335
+ "10": 0.4716417910447761
336
+ },
337
+ "pass@16": {
338
+ "2": 0.9885714285714285,
339
+ "3": 0.9708454810495627,
340
+ "4": 0.7777777777777778,
341
+ "5": 0.6529411764705882,
342
+ "6": 0.6403785488958991,
343
+ "7": 0.5253164556962026,
344
+ "8": 0.5255255255255256,
345
+ "9": 0.5594855305466238,
346
+ "10": 0.4925373134328358
347
+ },
348
+ "pass@32": {
349
+ "2": 0.9942857142857143,
350
+ "3": 0.9737609329446064,
351
+ "4": 0.7894736842105263,
352
+ "5": 0.6764705882352942,
353
+ "6": 0.6624605678233438,
354
+ "7": 0.5474683544303798,
355
+ "8": 0.5435435435435435,
356
+ "9": 0.5787781350482315,
357
+ "10": 0.49850746268656715
358
+ },
359
+ "pass@64": {
360
+ "2": 0.9971428571428571,
361
+ "3": 0.9795918367346939,
362
+ "4": 0.8157894736842105,
363
+ "5": 0.6911764705882353,
364
+ "6": 0.6845425867507886,
365
+ "7": 0.569620253164557,
366
+ "8": 0.5615615615615616,
367
+ "9": 0.5852090032154341,
368
+ "10": 0.5074626865671642
369
+ },
370
+ "pass@128": {
371
+ "2": 0.9971428571428571,
372
+ "3": 0.9825072886297376,
373
+ "4": 0.8362573099415205,
374
+ "5": 0.6941176470588235,
375
+ "6": 0.6908517350157729,
376
+ "7": 0.5886075949367089,
377
+ "8": 0.5855855855855856,
378
+ "9": 0.6012861736334405,
379
+ "10": 0.5223880597014925
380
+ }
381
+ },
382
+ "total_pass_at_k": {
383
+ "pass@1": 0.5932373619015735,
384
+ "pass@2": 0.6243722798794777,
385
+ "pass@4": 0.647472380314697,
386
+ "pass@8": 0.6672246401071309,
387
+ "pass@16": 0.6863073317710077,
388
+ "pass@32": 0.7007030465349849,
389
+ "pass@64": 0.7147639772346837,
390
+ "pass@128": 0.7264814194844326
391
+ }
392
+ },
393
+ "teachers_in_school": {
394
+ "per_op_pass_at_k": {
395
+ "2": {
396
+ "pass@1": 0.9544072948328267,
397
+ "pass@2": 0.9604863221884499,
398
+ "pass@4": 0.9665653495440729,
399
+ "pass@8": 0.9817629179331308,
400
+ "pass@16": 0.9817629179331308,
401
+ "pass@32": 0.9848024316109423,
402
+ "pass@64": 0.9848024316109423,
403
+ "pass@128": 0.9848024316109423
404
+ },
405
+ "3": {
406
+ "pass@1": 0.9212121212121213,
407
+ "pass@2": 0.9424242424242424,
408
+ "pass@4": 0.9575757575757575,
409
+ "pass@8": 0.9636363636363636,
410
+ "pass@16": 0.9696969696969697,
411
+ "pass@32": 0.9696969696969697,
412
+ "pass@64": 0.9757575757575757,
413
+ "pass@128": 0.9818181818181818
414
+ },
415
+ "4": {
416
+ "pass@1": 0.6627218934911243,
417
+ "pass@2": 0.7041420118343196,
418
+ "pass@4": 0.7337278106508875,
419
+ "pass@8": 0.7692307692307693,
420
+ "pass@16": 0.7810650887573964,
421
+ "pass@32": 0.7928994082840237,
422
+ "pass@64": 0.8076923076923077,
423
+ "pass@128": 0.8195266272189349
424
+ },
425
+ "5": {
426
+ "pass@1": 0.5768115942028985,
427
+ "pass@2": 0.591304347826087,
428
+ "pass@4": 0.6173913043478261,
429
+ "pass@8": 0.6608695652173913,
430
+ "pass@16": 0.6840579710144927,
431
+ "pass@32": 0.7043478260869566,
432
+ "pass@64": 0.7246376811594203,
433
+ "pass@128": 0.7391304347826086
434
+ },
435
+ "6": {
436
+ "pass@1": 0.5071633237822349,
437
+ "pass@2": 0.5415472779369628,
438
+ "pass@4": 0.5673352435530086,
439
+ "pass@8": 0.5959885386819485,
440
+ "pass@16": 0.6103151862464183,
441
+ "pass@32": 0.6189111747851003,
442
+ "pass@64": 0.6475644699140402,
443
+ "pass@128": 0.66189111747851
444
+ },
445
+ "7": {
446
+ "pass@1": 0.4595375722543353,
447
+ "pass@2": 0.4884393063583815,
448
+ "pass@4": 0.5057803468208093,
449
+ "pass@8": 0.5260115606936416,
450
+ "pass@16": 0.5578034682080925,
451
+ "pass@32": 0.5809248554913294,
452
+ "pass@64": 0.5982658959537572,
453
+ "pass@128": 0.615606936416185
454
+ },
455
+ "8": {
456
+ "pass@1": 0.4084507042253521,
457
+ "pass@2": 0.4507042253521127,
458
+ "pass@4": 0.4732394366197183,
459
+ "pass@8": 0.504225352112676,
460
+ "pass@16": 0.5154929577464789,
461
+ "pass@32": 0.532394366197183,
462
+ "pass@64": 0.543661971830986,
463
+ "pass@128": 0.5521126760563381
464
+ },
465
+ "9": {
466
+ "pass@1": 0.40119760479041916,
467
+ "pass@2": 0.44011976047904194,
468
+ "pass@4": 0.45808383233532934,
469
+ "pass@8": 0.47005988023952094,
470
+ "pass@16": 0.4940119760479042,
471
+ "pass@32": 0.5119760479041916,
472
+ "pass@64": 0.5269461077844312,
473
+ "pass@128": 0.5389221556886228
474
+ },
475
+ "10": {
476
+ "pass@1": 0.46932515337423314,
477
+ "pass@2": 0.49079754601226994,
478
+ "pass@4": 0.5,
479
+ "pass@8": 0.50920245398773,
480
+ "pass@16": 0.5245398773006135,
481
+ "pass@32": 0.5276073619631901,
482
+ "pass@64": 0.5368098159509203,
483
+ "pass@128": 0.5460122699386503
484
+ }
485
+ },
486
+ "per_op_pass_at_columns": {
487
+ "pass@1": {
488
+ "2": 0.9544072948328267,
489
+ "3": 0.9212121212121213,
490
+ "4": 0.6627218934911243,
491
+ "5": 0.5768115942028985,
492
+ "6": 0.5071633237822349,
493
+ "7": 0.4595375722543353,
494
+ "8": 0.4084507042253521,
495
+ "9": 0.40119760479041916,
496
+ "10": 0.46932515337423314
497
+ },
498
+ "pass@2": {
499
+ "2": 0.9604863221884499,
500
+ "3": 0.9424242424242424,
501
+ "4": 0.7041420118343196,
502
+ "5": 0.591304347826087,
503
+ "6": 0.5415472779369628,
504
+ "7": 0.4884393063583815,
505
+ "8": 0.4507042253521127,
506
+ "9": 0.44011976047904194,
507
+ "10": 0.49079754601226994
508
+ },
509
+ "pass@4": {
510
+ "2": 0.9665653495440729,
511
+ "3": 0.9575757575757575,
512
+ "4": 0.7337278106508875,
513
+ "5": 0.6173913043478261,
514
+ "6": 0.5673352435530086,
515
+ "7": 0.5057803468208093,
516
+ "8": 0.4732394366197183,
517
+ "9": 0.45808383233532934,
518
+ "10": 0.5
519
+ },
520
+ "pass@8": {
521
+ "2": 0.9817629179331308,
522
+ "3": 0.9636363636363636,
523
+ "4": 0.7692307692307693,
524
+ "5": 0.6608695652173913,
525
+ "6": 0.5959885386819485,
526
+ "7": 0.5260115606936416,
527
+ "8": 0.504225352112676,
528
+ "9": 0.47005988023952094,
529
+ "10": 0.50920245398773
530
+ },
531
+ "pass@16": {
532
+ "2": 0.9817629179331308,
533
+ "3": 0.9696969696969697,
534
+ "4": 0.7810650887573964,
535
+ "5": 0.6840579710144927,
536
+ "6": 0.6103151862464183,
537
+ "7": 0.5578034682080925,
538
+ "8": 0.5154929577464789,
539
+ "9": 0.4940119760479042,
540
+ "10": 0.5245398773006135
541
+ },
542
+ "pass@32": {
543
+ "2": 0.9848024316109423,
544
+ "3": 0.9696969696969697,
545
+ "4": 0.7928994082840237,
546
+ "5": 0.7043478260869566,
547
+ "6": 0.6189111747851003,
548
+ "7": 0.5809248554913294,
549
+ "8": 0.532394366197183,
550
+ "9": 0.5119760479041916,
551
+ "10": 0.5276073619631901
552
+ },
553
+ "pass@64": {
554
+ "2": 0.9848024316109423,
555
+ "3": 0.9757575757575757,
556
+ "4": 0.8076923076923077,
557
+ "5": 0.7246376811594203,
558
+ "6": 0.6475644699140402,
559
+ "7": 0.5982658959537572,
560
+ "8": 0.543661971830986,
561
+ "9": 0.5269461077844312,
562
+ "10": 0.5368098159509203
563
+ },
564
+ "pass@128": {
565
+ "2": 0.9848024316109423,
566
+ "3": 0.9818181818181818,
567
+ "4": 0.8195266272189349,
568
+ "5": 0.7391304347826086,
569
+ "6": 0.66189111747851,
570
+ "7": 0.615606936416185,
571
+ "8": 0.5521126760563381,
572
+ "9": 0.5389221556886228,
573
+ "10": 0.5460122699386503
574
+ }
575
+ },
576
+ "total_pass_at_k": {
577
+ "pass@1": 0.5927260812581914,
578
+ "pass@2": 0.6205766710353866,
579
+ "pass@4": 0.6395806028833552,
580
+ "pass@8": 0.6621887287024901,
581
+ "pass@16": 0.6775884665792923,
582
+ "pass@32": 0.6893840104849279,
583
+ "pass@64": 0.7031454783748362,
584
+ "pass@128": 0.7136304062909568
585
+ }
586
+ }
587
+ },
588
+ "total": {
589
+ "per_op_pass_at_k": {
590
+ "2": {
591
+ "pass@1": 0.944,
592
+ "pass@2": 0.968,
593
+ "pass@4": 0.976,
594
+ "pass@8": 0.984,
595
+ "pass@16": 0.986,
596
+ "pass@32": 0.99,
597
+ "pass@64": 0.991,
598
+ "pass@128": 0.992
599
+ },
600
+ "3": {
601
+ "pass@1": 0.914,
602
+ "pass@2": 0.939,
603
+ "pass@4": 0.95,
604
+ "pass@8": 0.959,
605
+ "pass@16": 0.967,
606
+ "pass@32": 0.969,
607
+ "pass@64": 0.978,
608
+ "pass@128": 0.981
609
+ },
610
+ "4": {
611
+ "pass@1": 0.676,
612
+ "pass@2": 0.706,
613
+ "pass@4": 0.733,
614
+ "pass@8": 0.754,
615
+ "pass@16": 0.768,
616
+ "pass@32": 0.783,
617
+ "pass@64": 0.801,
618
+ "pass@128": 0.818
619
+ },
620
+ "5": {
621
+ "pass@1": 0.56,
622
+ "pass@2": 0.582,
623
+ "pass@4": 0.609,
624
+ "pass@8": 0.643,
625
+ "pass@16": 0.668,
626
+ "pass@32": 0.689,
627
+ "pass@64": 0.705,
628
+ "pass@128": 0.716
629
+ },
630
+ "6": {
631
+ "pass@1": 0.512,
632
+ "pass@2": 0.554,
633
+ "pass@4": 0.583,
634
+ "pass@8": 0.62,
635
+ "pass@16": 0.639,
636
+ "pass@32": 0.658,
637
+ "pass@64": 0.681,
638
+ "pass@128": 0.693
639
+ },
640
+ "7": {
641
+ "pass@1": 0.457,
642
+ "pass@2": 0.493,
643
+ "pass@4": 0.517,
644
+ "pass@8": 0.532,
645
+ "pass@16": 0.561,
646
+ "pass@32": 0.584,
647
+ "pass@64": 0.602,
648
+ "pass@128": 0.62
649
+ },
650
+ "8": {
651
+ "pass@1": 0.432,
652
+ "pass@2": 0.463,
653
+ "pass@4": 0.486,
654
+ "pass@8": 0.508,
655
+ "pass@16": 0.527,
656
+ "pass@32": 0.545,
657
+ "pass@64": 0.559,
658
+ "pass@128": 0.576
659
+ },
660
+ "9": {
661
+ "pass@1": 0.424,
662
+ "pass@2": 0.463,
663
+ "pass@4": 0.492,
664
+ "pass@8": 0.514,
665
+ "pass@16": 0.539,
666
+ "pass@32": 0.555,
667
+ "pass@64": 0.569,
668
+ "pass@128": 0.58
669
+ },
670
+ "10": {
671
+ "pass@1": 0.452,
672
+ "pass@2": 0.477,
673
+ "pass@4": 0.49,
674
+ "pass@8": 0.5,
675
+ "pass@16": 0.516,
676
+ "pass@32": 0.519,
677
+ "pass@64": 0.527,
678
+ "pass@128": 0.539
679
+ }
680
+ },
681
+ "per_op_pass_at_columns": {
682
+ "pass@1": {
683
+ "2": 0.944,
684
+ "3": 0.914,
685
+ "4": 0.676,
686
+ "5": 0.56,
687
+ "6": 0.512,
688
+ "7": 0.457,
689
+ "8": 0.432,
690
+ "9": 0.424,
691
+ "10": 0.452
692
+ },
693
+ "pass@2": {
694
+ "2": 0.968,
695
+ "3": 0.939,
696
+ "4": 0.706,
697
+ "5": 0.582,
698
+ "6": 0.554,
699
+ "7": 0.493,
700
+ "8": 0.463,
701
+ "9": 0.463,
702
+ "10": 0.477
703
+ },
704
+ "pass@4": {
705
+ "2": 0.976,
706
+ "3": 0.95,
707
+ "4": 0.733,
708
+ "5": 0.609,
709
+ "6": 0.583,
710
+ "7": 0.517,
711
+ "8": 0.486,
712
+ "9": 0.492,
713
+ "10": 0.49
714
+ },
715
+ "pass@8": {
716
+ "2": 0.984,
717
+ "3": 0.959,
718
+ "4": 0.754,
719
+ "5": 0.643,
720
+ "6": 0.62,
721
+ "7": 0.532,
722
+ "8": 0.508,
723
+ "9": 0.514,
724
+ "10": 0.5
725
+ },
726
+ "pass@16": {
727
+ "2": 0.986,
728
+ "3": 0.967,
729
+ "4": 0.768,
730
+ "5": 0.668,
731
+ "6": 0.639,
732
+ "7": 0.561,
733
+ "8": 0.527,
734
+ "9": 0.539,
735
+ "10": 0.516
736
+ },
737
+ "pass@32": {
738
+ "2": 0.99,
739
+ "3": 0.969,
740
+ "4": 0.783,
741
+ "5": 0.689,
742
+ "6": 0.658,
743
+ "7": 0.584,
744
+ "8": 0.545,
745
+ "9": 0.555,
746
+ "10": 0.519
747
+ },
748
+ "pass@64": {
749
+ "2": 0.991,
750
+ "3": 0.978,
751
+ "4": 0.801,
752
+ "5": 0.705,
753
+ "6": 0.681,
754
+ "7": 0.602,
755
+ "8": 0.559,
756
+ "9": 0.569,
757
+ "10": 0.527
758
+ },
759
+ "pass@128": {
760
+ "2": 0.992,
761
+ "3": 0.981,
762
+ "4": 0.818,
763
+ "5": 0.716,
764
+ "6": 0.693,
765
+ "7": 0.62,
766
+ "8": 0.576,
767
+ "9": 0.58,
768
+ "10": 0.539
769
+ }
770
+ },
771
+ "total_pass_at_k": {
772
+ "pass@1": 0.5967777777777777,
773
+ "pass@2": 0.6272222222222222,
774
+ "pass@4": 0.6484444444444445,
775
+ "pass@8": 0.6682222222222223,
776
+ "pass@16": 0.6856666666666666,
777
+ "pass@32": 0.6991111111111111,
778
+ "pass@64": 0.7125555555555556,
779
+ "pass@128": 0.7238888888888889
780
+ }
781
+ },
782
+ "ks": [
783
+ 1,
784
+ 2,
785
+ 4,
786
+ 8,
787
+ 16,
788
+ 32,
789
+ 64,
790
+ 128
791
+ ],
792
+ "prompt_counts": {
793
+ "per_template": {
794
+ "crazy_zootopia": {
795
+ "per_op": {
796
+ "2": 321,
797
+ "3": 327,
798
+ "4": 320,
799
+ "5": 315,
800
+ "6": 334,
801
+ "7": 338,
802
+ "8": 312,
803
+ "9": 355,
804
+ "10": 339
805
+ },
806
+ "total": 2961
807
+ },
808
+ "movie_festival_awards": {
809
+ "per_op": {
810
+ "2": 350,
811
+ "3": 343,
812
+ "4": 342,
813
+ "5": 340,
814
+ "6": 317,
815
+ "7": 316,
816
+ "8": 333,
817
+ "9": 311,
818
+ "10": 335
819
+ },
820
+ "total": 2987
821
+ },
822
+ "teachers_in_school": {
823
+ "per_op": {
824
+ "2": 329,
825
+ "3": 330,
826
+ "4": 338,
827
+ "5": 345,
828
+ "6": 349,
829
+ "7": 346,
830
+ "8": 355,
831
+ "9": 334,
832
+ "10": 326
833
+ },
834
+ "total": 3052
835
+ }
836
+ },
837
+ "total": {
838
+ "per_op": {
839
+ "2": 1000,
840
+ "3": 1000,
841
+ "4": 1000,
842
+ "5": 1000,
843
+ "6": 1000,
844
+ "7": 1000,
845
+ "8": 1000,
846
+ "9": 1000,
847
+ "10": 1000
848
+ },
849
+ "total": 9000
850
+ }
851
+ }
852
+ },
853
+ "opd050302_refkl_s020_merged_hf_ood_generations.jsonl.graph_results.jsonl": {
854
+ "per_template": {
855
+ "crazy_zootopia": {
856
+ "per_op_pass_at_k": {
857
+ "11": {
858
+ "pass@1": 0.35127478753541075,
859
+ "pass@2": 0.37677053824362605,
860
+ "pass@4": 0.41076487252124644,
861
+ "pass@8": 0.42209631728045327,
862
+ "pass@16": 0.43059490084985835,
863
+ "pass@32": 0.4475920679886686,
864
+ "pass@64": 0.46458923512747874,
865
+ "pass@128": 0.48158640226628896
866
+ },
867
+ "12": {
868
+ "pass@1": 0.3870056497175141,
869
+ "pass@2": 0.4491525423728814,
870
+ "pass@4": 0.4689265536723164,
871
+ "pass@8": 0.4915254237288136,
872
+ "pass@16": 0.5084745762711864,
873
+ "pass@32": 0.5169491525423728,
874
+ "pass@64": 0.5282485875706214,
875
+ "pass@128": 0.5282485875706214
876
+ },
877
+ "13": {
878
+ "pass@1": 0.25705329153605017,
879
+ "pass@2": 0.31347962382445144,
880
+ "pass@4": 0.34796238244514105,
881
+ "pass@8": 0.3761755485893417,
882
+ "pass@16": 0.41379310344827586,
883
+ "pass@32": 0.43260188087774293,
884
+ "pass@64": 0.4482758620689655,
885
+ "pass@128": 0.45768025078369906
886
+ },
887
+ "14": {
888
+ "pass@1": 0.17757009345794392,
889
+ "pass@2": 0.23052959501557632,
890
+ "pass@4": 0.2803738317757009,
891
+ "pass@8": 0.3146417445482866,
892
+ "pass@16": 0.3426791277258567,
893
+ "pass@32": 0.3862928348909657,
894
+ "pass@64": 0.411214953271028,
895
+ "pass@128": 0.43302180685358255
896
+ },
897
+ "15": {
898
+ "pass@1": 0.11560693641618497,
899
+ "pass@2": 0.14450867052023122,
900
+ "pass@4": 0.17341040462427745,
901
+ "pass@8": 0.21965317919075145,
902
+ "pass@16": 0.2630057803468208,
903
+ "pass@32": 0.2774566473988439,
904
+ "pass@64": 0.315028901734104,
905
+ "pass@128": 0.33815028901734107
906
+ },
907
+ "16": {
908
+ "pass@1": 0.07741935483870968,
909
+ "pass@2": 0.13225806451612904,
910
+ "pass@4": 0.15806451612903225,
911
+ "pass@8": 0.2032258064516129,
912
+ "pass@16": 0.23548387096774193,
913
+ "pass@32": 0.27741935483870966,
914
+ "pass@64": 0.3032258064516129,
915
+ "pass@128": 0.3193548387096774
916
+ },
917
+ "17": {
918
+ "pass@1": 0.028901734104046242,
919
+ "pass@2": 0.046242774566473986,
920
+ "pass@4": 0.07803468208092486,
921
+ "pass@8": 0.12138728323699421,
922
+ "pass@16": 0.1531791907514451,
923
+ "pass@32": 0.18208092485549132,
924
+ "pass@64": 0.22254335260115607,
925
+ "pass@128": 0.2514450867052023
926
+ },
927
+ "18": {
928
+ "pass@1": 0.03142857142857143,
929
+ "pass@2": 0.04,
930
+ "pass@4": 0.05142857142857143,
931
+ "pass@8": 0.06571428571428571,
932
+ "pass@16": 0.08571428571428572,
933
+ "pass@32": 0.1,
934
+ "pass@64": 0.12,
935
+ "pass@128": 0.14
936
+ },
937
+ "19": {
938
+ "pass@1": 0.003003003003003003,
939
+ "pass@2": 0.003003003003003003,
940
+ "pass@4": 0.006006006006006006,
941
+ "pass@8": 0.015015015015015015,
942
+ "pass@16": 0.024024024024024024,
943
+ "pass@32": 0.042042042042042045,
944
+ "pass@64": 0.04804804804804805,
945
+ "pass@128": 0.06006006006006006
946
+ },
947
+ "20": {
948
+ "pass@1": 0.003003003003003003,
949
+ "pass@2": 0.006006006006006006,
950
+ "pass@4": 0.009009009009009009,
951
+ "pass@8": 0.021021021021021023,
952
+ "pass@16": 0.02702702702702703,
953
+ "pass@32": 0.03003003003003003,
954
+ "pass@64": 0.03303303303303303,
955
+ "pass@128": 0.04504504504504504
956
+ }
957
+ },
958
+ "per_op_pass_at_columns": {
959
+ "pass@1": {
960
+ "11": 0.35127478753541075,
961
+ "12": 0.3870056497175141,
962
+ "13": 0.25705329153605017,
963
+ "14": 0.17757009345794392,
964
+ "15": 0.11560693641618497,
965
+ "16": 0.07741935483870968,
966
+ "17": 0.028901734104046242,
967
+ "18": 0.03142857142857143,
968
+ "19": 0.003003003003003003,
969
+ "20": 0.003003003003003003
970
+ },
971
+ "pass@2": {
972
+ "11": 0.37677053824362605,
973
+ "12": 0.4491525423728814,
974
+ "13": 0.31347962382445144,
975
+ "14": 0.23052959501557632,
976
+ "15": 0.14450867052023122,
977
+ "16": 0.13225806451612904,
978
+ "17": 0.046242774566473986,
979
+ "18": 0.04,
980
+ "19": 0.003003003003003003,
981
+ "20": 0.006006006006006006
982
+ },
983
+ "pass@4": {
984
+ "11": 0.41076487252124644,
985
+ "12": 0.4689265536723164,
986
+ "13": 0.34796238244514105,
987
+ "14": 0.2803738317757009,
988
+ "15": 0.17341040462427745,
989
+ "16": 0.15806451612903225,
990
+ "17": 0.07803468208092486,
991
+ "18": 0.05142857142857143,
992
+ "19": 0.006006006006006006,
993
+ "20": 0.009009009009009009
994
+ },
995
+ "pass@8": {
996
+ "11": 0.42209631728045327,
997
+ "12": 0.4915254237288136,
998
+ "13": 0.3761755485893417,
999
+ "14": 0.3146417445482866,
1000
+ "15": 0.21965317919075145,
1001
+ "16": 0.2032258064516129,
1002
+ "17": 0.12138728323699421,
1003
+ "18": 0.06571428571428571,
1004
+ "19": 0.015015015015015015,
1005
+ "20": 0.021021021021021023
1006
+ },
1007
+ "pass@16": {
1008
+ "11": 0.43059490084985835,
1009
+ "12": 0.5084745762711864,
1010
+ "13": 0.41379310344827586,
1011
+ "14": 0.3426791277258567,
1012
+ "15": 0.2630057803468208,
1013
+ "16": 0.23548387096774193,
1014
+ "17": 0.1531791907514451,
1015
+ "18": 0.08571428571428572,
1016
+ "19": 0.024024024024024024,
1017
+ "20": 0.02702702702702703
1018
+ },
1019
+ "pass@32": {
1020
+ "11": 0.4475920679886686,
1021
+ "12": 0.5169491525423728,
1022
+ "13": 0.43260188087774293,
1023
+ "14": 0.3862928348909657,
1024
+ "15": 0.2774566473988439,
1025
+ "16": 0.27741935483870966,
1026
+ "17": 0.18208092485549132,
1027
+ "18": 0.1,
1028
+ "19": 0.042042042042042045,
1029
+ "20": 0.03003003003003003
1030
+ },
1031
+ "pass@64": {
1032
+ "11": 0.46458923512747874,
1033
+ "12": 0.5282485875706214,
1034
+ "13": 0.4482758620689655,
1035
+ "14": 0.411214953271028,
1036
+ "15": 0.315028901734104,
1037
+ "16": 0.3032258064516129,
1038
+ "17": 0.22254335260115607,
1039
+ "18": 0.12,
1040
+ "19": 0.04804804804804805,
1041
+ "20": 0.03303303303303303
1042
+ },
1043
+ "pass@128": {
1044
+ "11": 0.48158640226628896,
1045
+ "12": 0.5282485875706214,
1046
+ "13": 0.45768025078369906,
1047
+ "14": 0.43302180685358255,
1048
+ "15": 0.33815028901734107,
1049
+ "16": 0.3193548387096774,
1050
+ "17": 0.2514450867052023,
1051
+ "18": 0.14,
1052
+ "19": 0.06006006006006006,
1053
+ "20": 0.04504504504504504
1054
+ }
1055
+ },
1056
+ "total_pass_at_k": {
1057
+ "pass@1": 0.1447251114413076,
1058
+ "pass@2": 0.17533432392273401,
1059
+ "pass@4": 0.19940564635958397,
1060
+ "pass@8": 0.22585438335809807,
1061
+ "pass@16": 0.24903417533432393,
1062
+ "pass@32": 0.26953937592867755,
1063
+ "pass@64": 0.2897473997028232,
1064
+ "pass@128": 0.3057949479940565
1065
+ }
1066
+ },
1067
+ "movie_festival_awards": {
1068
+ "per_op_pass_at_k": {
1069
+ "11": {
1070
+ "pass@1": 0.3492063492063492,
1071
+ "pass@2": 0.4031746031746032,
1072
+ "pass@4": 0.42857142857142855,
1073
+ "pass@8": 0.4507936507936508,
1074
+ "pass@16": 0.4666666666666667,
1075
+ "pass@32": 0.46984126984126984,
1076
+ "pass@64": 0.49206349206349204,
1077
+ "pass@128": 0.5047619047619047
1078
+ },
1079
+ "12": {
1080
+ "pass@1": 0.3853211009174312,
1081
+ "pass@2": 0.41896024464831805,
1082
+ "pass@4": 0.45565749235474007,
1083
+ "pass@8": 0.4801223241590214,
1084
+ "pass@16": 0.48623853211009177,
1085
+ "pass@32": 0.5015290519877675,
1086
+ "pass@64": 0.5137614678899083,
1087
+ "pass@128": 0.5321100917431193
1088
+ },
1089
+ "13": {
1090
+ "pass@1": 0.2623456790123457,
1091
+ "pass@2": 0.30864197530864196,
1092
+ "pass@4": 0.36728395061728397,
1093
+ "pass@8": 0.3950617283950617,
1094
+ "pass@16": 0.41358024691358025,
1095
+ "pass@32": 0.43209876543209874,
1096
+ "pass@64": 0.4444444444444444,
1097
+ "pass@128": 0.4660493827160494
1098
+ },
1099
+ "14": {
1100
+ "pass@1": 0.14836795252225518,
1101
+ "pass@2": 0.20771513353115728,
1102
+ "pass@4": 0.27299703264094954,
1103
+ "pass@8": 0.29080118694362017,
1104
+ "pass@16": 0.3115727002967359,
1105
+ "pass@32": 0.34421364985163205,
1106
+ "pass@64": 0.3620178041543027,
1107
+ "pass@128": 0.37388724035608306
1108
+ },
1109
+ "15": {
1110
+ "pass@1": 0.09567901234567901,
1111
+ "pass@2": 0.13580246913580246,
1112
+ "pass@4": 0.17592592592592593,
1113
+ "pass@8": 0.21604938271604937,
1114
+ "pass@16": 0.25617283950617287,
1115
+ "pass@32": 0.27469135802469136,
1116
+ "pass@64": 0.2932098765432099,
1117
+ "pass@128": 0.3117283950617284
1118
+ },
1119
+ "16": {
1120
+ "pass@1": 0.0855457227138643,
1121
+ "pass@2": 0.11209439528023599,
1122
+ "pass@4": 0.15634218289085547,
1123
+ "pass@8": 0.22418879056047197,
1124
+ "pass@16": 0.24778761061946902,
1125
+ "pass@32": 0.26548672566371684,
1126
+ "pass@64": 0.2949852507374631,
1127
+ "pass@128": 0.3185840707964602
1128
+ },
1129
+ "17": {
1130
+ "pass@1": 0.02108433734939759,
1131
+ "pass@2": 0.03614457831325301,
1132
+ "pass@4": 0.05120481927710843,
1133
+ "pass@8": 0.08734939759036145,
1134
+ "pass@16": 0.10843373493975904,
1135
+ "pass@32": 0.13253012048192772,
1136
+ "pass@64": 0.1536144578313253,
1137
+ "pass@128": 0.17771084337349397
1138
+ },
1139
+ "18": {
1140
+ "pass@1": 0.025806451612903226,
1141
+ "pass@2": 0.041935483870967745,
1142
+ "pass@4": 0.05161290322580645,
1143
+ "pass@8": 0.06774193548387097,
1144
+ "pass@16": 0.07419354838709677,
1145
+ "pass@32": 0.0967741935483871,
1146
+ "pass@64": 0.11290322580645161,
1147
+ "pass@128": 0.12258064516129032
1148
+ },
1149
+ "19": {
1150
+ "pass@1": 0.0030211480362537764,
1151
+ "pass@2": 0.006042296072507553,
1152
+ "pass@4": 0.00906344410876133,
1153
+ "pass@8": 0.012084592145015106,
1154
+ "pass@16": 0.01812688821752266,
1155
+ "pass@32": 0.01812688821752266,
1156
+ "pass@64": 0.04229607250755287,
1157
+ "pass@128": 0.054380664652567974
1158
+ },
1159
+ "20": {
1160
+ "pass@1": 0.0,
1161
+ "pass@2": 0.0,
1162
+ "pass@4": 0.003003003003003003,
1163
+ "pass@8": 0.003003003003003003,
1164
+ "pass@16": 0.003003003003003003,
1165
+ "pass@32": 0.009009009009009009,
1166
+ "pass@64": 0.015015015015015015,
1167
+ "pass@128": 0.021021021021021023
1168
+ }
1169
+ },
1170
+ "per_op_pass_at_columns": {
1171
+ "pass@1": {
1172
+ "11": 0.3492063492063492,
1173
+ "12": 0.3853211009174312,
1174
+ "13": 0.2623456790123457,
1175
+ "14": 0.14836795252225518,
1176
+ "15": 0.09567901234567901,
1177
+ "16": 0.0855457227138643,
1178
+ "17": 0.02108433734939759,
1179
+ "18": 0.025806451612903226,
1180
+ "19": 0.0030211480362537764,
1181
+ "20": 0.0
1182
+ },
1183
+ "pass@2": {
1184
+ "11": 0.4031746031746032,
1185
+ "12": 0.41896024464831805,
1186
+ "13": 0.30864197530864196,
1187
+ "14": 0.20771513353115728,
1188
+ "15": 0.13580246913580246,
1189
+ "16": 0.11209439528023599,
1190
+ "17": 0.03614457831325301,
1191
+ "18": 0.041935483870967745,
1192
+ "19": 0.006042296072507553,
1193
+ "20": 0.0
1194
+ },
1195
+ "pass@4": {
1196
+ "11": 0.42857142857142855,
1197
+ "12": 0.45565749235474007,
1198
+ "13": 0.36728395061728397,
1199
+ "14": 0.27299703264094954,
1200
+ "15": 0.17592592592592593,
1201
+ "16": 0.15634218289085547,
1202
+ "17": 0.05120481927710843,
1203
+ "18": 0.05161290322580645,
1204
+ "19": 0.00906344410876133,
1205
+ "20": 0.003003003003003003
1206
+ },
1207
+ "pass@8": {
1208
+ "11": 0.4507936507936508,
1209
+ "12": 0.4801223241590214,
1210
+ "13": 0.3950617283950617,
1211
+ "14": 0.29080118694362017,
1212
+ "15": 0.21604938271604937,
1213
+ "16": 0.22418879056047197,
1214
+ "17": 0.08734939759036145,
1215
+ "18": 0.06774193548387097,
1216
+ "19": 0.012084592145015106,
1217
+ "20": 0.003003003003003003
1218
+ },
1219
+ "pass@16": {
1220
+ "11": 0.4666666666666667,
1221
+ "12": 0.48623853211009177,
1222
+ "13": 0.41358024691358025,
1223
+ "14": 0.3115727002967359,
1224
+ "15": 0.25617283950617287,
1225
+ "16": 0.24778761061946902,
1226
+ "17": 0.10843373493975904,
1227
+ "18": 0.07419354838709677,
1228
+ "19": 0.01812688821752266,
1229
+ "20": 0.003003003003003003
1230
+ },
1231
+ "pass@32": {
1232
+ "11": 0.46984126984126984,
1233
+ "12": 0.5015290519877675,
1234
+ "13": 0.43209876543209874,
1235
+ "14": 0.34421364985163205,
1236
+ "15": 0.27469135802469136,
1237
+ "16": 0.26548672566371684,
1238
+ "17": 0.13253012048192772,
1239
+ "18": 0.0967741935483871,
1240
+ "19": 0.01812688821752266,
1241
+ "20": 0.009009009009009009
1242
+ },
1243
+ "pass@64": {
1244
+ "11": 0.49206349206349204,
1245
+ "12": 0.5137614678899083,
1246
+ "13": 0.4444444444444444,
1247
+ "14": 0.3620178041543027,
1248
+ "15": 0.2932098765432099,
1249
+ "16": 0.2949852507374631,
1250
+ "17": 0.1536144578313253,
1251
+ "18": 0.11290322580645161,
1252
+ "19": 0.04229607250755287,
1253
+ "20": 0.015015015015015015
1254
+ },
1255
+ "pass@128": {
1256
+ "11": 0.5047619047619047,
1257
+ "12": 0.5321100917431193,
1258
+ "13": 0.4660493827160494,
1259
+ "14": 0.37388724035608306,
1260
+ "15": 0.3117283950617284,
1261
+ "16": 0.3185840707964602,
1262
+ "17": 0.17771084337349397,
1263
+ "18": 0.12258064516129032,
1264
+ "19": 0.054380664652567974,
1265
+ "20": 0.021021021021021023
1266
+ }
1267
+ },
1268
+ "total_pass_at_k": {
1269
+ "pass@1": 0.13661369193154035,
1270
+ "pass@2": 0.16595354523227385,
1271
+ "pass@4": 0.19621026894865526,
1272
+ "pass@8": 0.22188264058679708,
1273
+ "pass@16": 0.23777506112469438,
1274
+ "pass@32": 0.2536674816625917,
1275
+ "pass@64": 0.2716992665036675,
1276
+ "pass@128": 0.2875916870415648
1277
+ }
1278
+ },
1279
+ "teachers_in_school": {
1280
+ "per_op_pass_at_k": {
1281
+ "11": {
1282
+ "pass@1": 0.4036144578313253,
1283
+ "pass@2": 0.463855421686747,
1284
+ "pass@4": 0.4819277108433735,
1285
+ "pass@8": 0.5180722891566265,
1286
+ "pass@16": 0.5391566265060241,
1287
+ "pass@32": 0.5481927710843374,
1288
+ "pass@64": 0.5662650602409639,
1289
+ "pass@128": 0.5813253012048193
1290
+ },
1291
+ "12": {
1292
+ "pass@1": 0.34169278996865204,
1293
+ "pass@2": 0.3667711598746082,
1294
+ "pass@4": 0.3949843260188088,
1295
+ "pass@8": 0.4169278996865204,
1296
+ "pass@16": 0.42946708463949845,
1297
+ "pass@32": 0.44200626959247646,
1298
+ "pass@64": 0.45454545454545453,
1299
+ "pass@128": 0.4670846394984326
1300
+ },
1301
+ "13": {
1302
+ "pass@1": 0.25770308123249297,
1303
+ "pass@2": 0.32212885154061627,
1304
+ "pass@4": 0.3641456582633053,
1305
+ "pass@8": 0.39215686274509803,
1306
+ "pass@16": 0.4117647058823529,
1307
+ "pass@32": 0.4341736694677871,
1308
+ "pass@64": 0.44537815126050423,
1309
+ "pass@128": 0.45938375350140054
1310
+ },
1311
+ "14": {
1312
+ "pass@1": 0.1783625730994152,
1313
+ "pass@2": 0.2543859649122807,
1314
+ "pass@4": 0.29239766081871343,
1315
+ "pass@8": 0.3362573099415205,
1316
+ "pass@16": 0.35964912280701755,
1317
+ "pass@32": 0.3830409356725146,
1318
+ "pass@64": 0.4093567251461988,
1319
+ "pass@128": 0.4502923976608187
1320
+ },
1321
+ "15": {
1322
+ "pass@1": 0.12727272727272726,
1323
+ "pass@2": 0.15757575757575756,
1324
+ "pass@4": 0.18787878787878787,
1325
+ "pass@8": 0.21818181818181817,
1326
+ "pass@16": 0.24848484848484848,
1327
+ "pass@32": 0.2787878787878788,
1328
+ "pass@64": 0.30303030303030304,
1329
+ "pass@128": 0.3393939393939394
1330
+ },
1331
+ "16": {
1332
+ "pass@1": 0.08547008547008547,
1333
+ "pass@2": 0.11396011396011396,
1334
+ "pass@4": 0.15954415954415954,
1335
+ "pass@8": 0.20512820512820512,
1336
+ "pass@16": 0.24786324786324787,
1337
+ "pass@32": 0.2792022792022792,
1338
+ "pass@64": 0.3162393162393162,
1339
+ "pass@128": 0.33903133903133903
1340
+ },
1341
+ "17": {
1342
+ "pass@1": 0.037267080745341616,
1343
+ "pass@2": 0.049689440993788817,
1344
+ "pass@4": 0.07763975155279502,
1345
+ "pass@8": 0.10869565217391304,
1346
+ "pass@16": 0.15217391304347827,
1347
+ "pass@32": 0.17701863354037267,
1348
+ "pass@64": 0.1956521739130435,
1349
+ "pass@128": 0.2204968944099379
1350
+ },
1351
+ "18": {
1352
+ "pass@1": 0.023529411764705882,
1353
+ "pass@2": 0.03823529411764706,
1354
+ "pass@4": 0.05588235294117647,
1355
+ "pass@8": 0.06764705882352941,
1356
+ "pass@16": 0.09117647058823529,
1357
+ "pass@32": 0.11470588235294117,
1358
+ "pass@64": 0.13823529411764707,
1359
+ "pass@128": 0.16470588235294117
1360
+ },
1361
+ "19": {
1362
+ "pass@1": 0.002976190476190476,
1363
+ "pass@2": 0.008928571428571428,
1364
+ "pass@4": 0.017857142857142856,
1365
+ "pass@8": 0.026785714285714284,
1366
+ "pass@16": 0.03869047619047619,
1367
+ "pass@32": 0.041666666666666664,
1368
+ "pass@64": 0.044642857142857144,
1369
+ "pass@128": 0.05357142857142857
1370
+ },
1371
+ "20": {
1372
+ "pass@1": 0.0,
1373
+ "pass@2": 0.0,
1374
+ "pass@4": 0.0029940119760479044,
1375
+ "pass@8": 0.005988023952095809,
1376
+ "pass@16": 0.005988023952095809,
1377
+ "pass@32": 0.005988023952095809,
1378
+ "pass@64": 0.017964071856287425,
1379
+ "pass@128": 0.02694610778443114
1380
+ }
1381
+ },
1382
+ "per_op_pass_at_columns": {
1383
+ "pass@1": {
1384
+ "11": 0.4036144578313253,
1385
+ "12": 0.34169278996865204,
1386
+ "13": 0.25770308123249297,
1387
+ "14": 0.1783625730994152,
1388
+ "15": 0.12727272727272726,
1389
+ "16": 0.08547008547008547,
1390
+ "17": 0.037267080745341616,
1391
+ "18": 0.023529411764705882,
1392
+ "19": 0.002976190476190476,
1393
+ "20": 0.0
1394
+ },
1395
+ "pass@2": {
1396
+ "11": 0.463855421686747,
1397
+ "12": 0.3667711598746082,
1398
+ "13": 0.32212885154061627,
1399
+ "14": 0.2543859649122807,
1400
+ "15": 0.15757575757575756,
1401
+ "16": 0.11396011396011396,
1402
+ "17": 0.049689440993788817,
1403
+ "18": 0.03823529411764706,
1404
+ "19": 0.008928571428571428,
1405
+ "20": 0.0
1406
+ },
1407
+ "pass@4": {
1408
+ "11": 0.4819277108433735,
1409
+ "12": 0.3949843260188088,
1410
+ "13": 0.3641456582633053,
1411
+ "14": 0.29239766081871343,
1412
+ "15": 0.18787878787878787,
1413
+ "16": 0.15954415954415954,
1414
+ "17": 0.07763975155279502,
1415
+ "18": 0.05588235294117647,
1416
+ "19": 0.017857142857142856,
1417
+ "20": 0.0029940119760479044
1418
+ },
1419
+ "pass@8": {
1420
+ "11": 0.5180722891566265,
1421
+ "12": 0.4169278996865204,
1422
+ "13": 0.39215686274509803,
1423
+ "14": 0.3362573099415205,
1424
+ "15": 0.21818181818181817,
1425
+ "16": 0.20512820512820512,
1426
+ "17": 0.10869565217391304,
1427
+ "18": 0.06764705882352941,
1428
+ "19": 0.026785714285714284,
1429
+ "20": 0.005988023952095809
1430
+ },
1431
+ "pass@16": {
1432
+ "11": 0.5391566265060241,
1433
+ "12": 0.42946708463949845,
1434
+ "13": 0.4117647058823529,
1435
+ "14": 0.35964912280701755,
1436
+ "15": 0.24848484848484848,
1437
+ "16": 0.24786324786324787,
1438
+ "17": 0.15217391304347827,
1439
+ "18": 0.09117647058823529,
1440
+ "19": 0.03869047619047619,
1441
+ "20": 0.005988023952095809
1442
+ },
1443
+ "pass@32": {
1444
+ "11": 0.5481927710843374,
1445
+ "12": 0.44200626959247646,
1446
+ "13": 0.4341736694677871,
1447
+ "14": 0.3830409356725146,
1448
+ "15": 0.2787878787878788,
1449
+ "16": 0.2792022792022792,
1450
+ "17": 0.17701863354037267,
1451
+ "18": 0.11470588235294117,
1452
+ "19": 0.041666666666666664,
1453
+ "20": 0.005988023952095809
1454
+ },
1455
+ "pass@64": {
1456
+ "11": 0.5662650602409639,
1457
+ "12": 0.45454545454545453,
1458
+ "13": 0.44537815126050423,
1459
+ "14": 0.4093567251461988,
1460
+ "15": 0.30303030303030304,
1461
+ "16": 0.3162393162393162,
1462
+ "17": 0.1956521739130435,
1463
+ "18": 0.13823529411764707,
1464
+ "19": 0.044642857142857144,
1465
+ "20": 0.017964071856287425
1466
+ },
1467
+ "pass@128": {
1468
+ "11": 0.5813253012048193,
1469
+ "12": 0.4670846394984326,
1470
+ "13": 0.45938375350140054,
1471
+ "14": 0.4502923976608187,
1472
+ "15": 0.3393939393939394,
1473
+ "16": 0.33903133903133903,
1474
+ "17": 0.2204968944099379,
1475
+ "18": 0.16470588235294117,
1476
+ "19": 0.05357142857142857,
1477
+ "20": 0.02694610778443114
1478
+ }
1479
+ },
1480
+ "total_pass_at_k": {
1481
+ "pass@1": 0.14540588760035683,
1482
+ "pass@2": 0.17752007136485282,
1483
+ "pass@4": 0.20368718406184955,
1484
+ "pass@8": 0.22985429675884628,
1485
+ "pass@16": 0.2527505203687184,
1486
+ "pass@32": 0.27088908712459114,
1487
+ "pass@64": 0.2896223609872138,
1488
+ "pass@128": 0.3107344632768362
1489
+ }
1490
+ }
1491
+ },
1492
+ "total": {
1493
+ "per_op_pass_at_k": {
1494
+ "11": {
1495
+ "pass@1": 0.368,
1496
+ "pass@2": 0.414,
1497
+ "pass@4": 0.44,
1498
+ "pass@8": 0.463,
1499
+ "pass@16": 0.478,
1500
+ "pass@32": 0.488,
1501
+ "pass@64": 0.507,
1502
+ "pass@128": 0.522
1503
+ },
1504
+ "12": {
1505
+ "pass@1": 0.372,
1506
+ "pass@2": 0.413,
1507
+ "pass@4": 0.441,
1508
+ "pass@8": 0.464,
1509
+ "pass@16": 0.476,
1510
+ "pass@32": 0.488,
1511
+ "pass@64": 0.5,
1512
+ "pass@128": 0.51
1513
+ },
1514
+ "13": {
1515
+ "pass@1": 0.259,
1516
+ "pass@2": 0.315,
1517
+ "pass@4": 0.36,
1518
+ "pass@8": 0.388,
1519
+ "pass@16": 0.413,
1520
+ "pass@32": 0.433,
1521
+ "pass@64": 0.446,
1522
+ "pass@128": 0.461
1523
+ },
1524
+ "14": {
1525
+ "pass@1": 0.168,
1526
+ "pass@2": 0.231,
1527
+ "pass@4": 0.282,
1528
+ "pass@8": 0.314,
1529
+ "pass@16": 0.338,
1530
+ "pass@32": 0.371,
1531
+ "pass@64": 0.394,
1532
+ "pass@128": 0.419
1533
+ },
1534
+ "15": {
1535
+ "pass@1": 0.113,
1536
+ "pass@2": 0.146,
1537
+ "pass@4": 0.179,
1538
+ "pass@8": 0.218,
1539
+ "pass@16": 0.256,
1540
+ "pass@32": 0.277,
1541
+ "pass@64": 0.304,
1542
+ "pass@128": 0.33
1543
+ },
1544
+ "16": {
1545
+ "pass@1": 0.083,
1546
+ "pass@2": 0.119,
1547
+ "pass@4": 0.158,
1548
+ "pass@8": 0.211,
1549
+ "pass@16": 0.244,
1550
+ "pass@32": 0.274,
1551
+ "pass@64": 0.305,
1552
+ "pass@128": 0.326
1553
+ },
1554
+ "17": {
1555
+ "pass@1": 0.029,
1556
+ "pass@2": 0.044,
1557
+ "pass@4": 0.069,
1558
+ "pass@8": 0.106,
1559
+ "pass@16": 0.138,
1560
+ "pass@32": 0.164,
1561
+ "pass@64": 0.191,
1562
+ "pass@128": 0.217
1563
+ },
1564
+ "18": {
1565
+ "pass@1": 0.027,
1566
+ "pass@2": 0.04,
1567
+ "pass@4": 0.053,
1568
+ "pass@8": 0.067,
1569
+ "pass@16": 0.084,
1570
+ "pass@32": 0.104,
1571
+ "pass@64": 0.124,
1572
+ "pass@128": 0.143
1573
+ },
1574
+ "19": {
1575
+ "pass@1": 0.003,
1576
+ "pass@2": 0.006,
1577
+ "pass@4": 0.011,
1578
+ "pass@8": 0.018,
1579
+ "pass@16": 0.027,
1580
+ "pass@32": 0.034,
1581
+ "pass@64": 0.045,
1582
+ "pass@128": 0.056
1583
+ },
1584
+ "20": {
1585
+ "pass@1": 0.001,
1586
+ "pass@2": 0.002,
1587
+ "pass@4": 0.005,
1588
+ "pass@8": 0.01,
1589
+ "pass@16": 0.012,
1590
+ "pass@32": 0.015,
1591
+ "pass@64": 0.022,
1592
+ "pass@128": 0.031
1593
+ }
1594
+ },
1595
+ "per_op_pass_at_columns": {
1596
+ "pass@1": {
1597
+ "11": 0.368,
1598
+ "12": 0.372,
1599
+ "13": 0.259,
1600
+ "14": 0.168,
1601
+ "15": 0.113,
1602
+ "16": 0.083,
1603
+ "17": 0.029,
1604
+ "18": 0.027,
1605
+ "19": 0.003,
1606
+ "20": 0.001
1607
+ },
1608
+ "pass@2": {
1609
+ "11": 0.414,
1610
+ "12": 0.413,
1611
+ "13": 0.315,
1612
+ "14": 0.231,
1613
+ "15": 0.146,
1614
+ "16": 0.119,
1615
+ "17": 0.044,
1616
+ "18": 0.04,
1617
+ "19": 0.006,
1618
+ "20": 0.002
1619
+ },
1620
+ "pass@4": {
1621
+ "11": 0.44,
1622
+ "12": 0.441,
1623
+ "13": 0.36,
1624
+ "14": 0.282,
1625
+ "15": 0.179,
1626
+ "16": 0.158,
1627
+ "17": 0.069,
1628
+ "18": 0.053,
1629
+ "19": 0.011,
1630
+ "20": 0.005
1631
+ },
1632
+ "pass@8": {
1633
+ "11": 0.463,
1634
+ "12": 0.464,
1635
+ "13": 0.388,
1636
+ "14": 0.314,
1637
+ "15": 0.218,
1638
+ "16": 0.211,
1639
+ "17": 0.106,
1640
+ "18": 0.067,
1641
+ "19": 0.018,
1642
+ "20": 0.01
1643
+ },
1644
+ "pass@16": {
1645
+ "11": 0.478,
1646
+ "12": 0.476,
1647
+ "13": 0.413,
1648
+ "14": 0.338,
1649
+ "15": 0.256,
1650
+ "16": 0.244,
1651
+ "17": 0.138,
1652
+ "18": 0.084,
1653
+ "19": 0.027,
1654
+ "20": 0.012
1655
+ },
1656
+ "pass@32": {
1657
+ "11": 0.488,
1658
+ "12": 0.488,
1659
+ "13": 0.433,
1660
+ "14": 0.371,
1661
+ "15": 0.277,
1662
+ "16": 0.274,
1663
+ "17": 0.164,
1664
+ "18": 0.104,
1665
+ "19": 0.034,
1666
+ "20": 0.015
1667
+ },
1668
+ "pass@64": {
1669
+ "11": 0.507,
1670
+ "12": 0.5,
1671
+ "13": 0.446,
1672
+ "14": 0.394,
1673
+ "15": 0.304,
1674
+ "16": 0.305,
1675
+ "17": 0.191,
1676
+ "18": 0.124,
1677
+ "19": 0.045,
1678
+ "20": 0.022
1679
+ },
1680
+ "pass@128": {
1681
+ "11": 0.522,
1682
+ "12": 0.51,
1683
+ "13": 0.461,
1684
+ "14": 0.419,
1685
+ "15": 0.33,
1686
+ "16": 0.326,
1687
+ "17": 0.217,
1688
+ "18": 0.143,
1689
+ "19": 0.056,
1690
+ "20": 0.031
1691
+ }
1692
+ },
1693
+ "total_pass_at_k": {
1694
+ "pass@1": 0.1423,
1695
+ "pass@2": 0.173,
1696
+ "pass@4": 0.1998,
1697
+ "pass@8": 0.2259,
1698
+ "pass@16": 0.2466,
1699
+ "pass@32": 0.2648,
1700
+ "pass@64": 0.2838,
1701
+ "pass@128": 0.3015
1702
+ }
1703
+ },
1704
+ "ks": [
1705
+ 1,
1706
+ 2,
1707
+ 4,
1708
+ 8,
1709
+ 16,
1710
+ 32,
1711
+ 64,
1712
+ 128
1713
+ ],
1714
+ "prompt_counts": {
1715
+ "per_template": {
1716
+ "crazy_zootopia": {
1717
+ "per_op": {
1718
+ "11": 353,
1719
+ "12": 354,
1720
+ "13": 319,
1721
+ "14": 321,
1722
+ "15": 346,
1723
+ "16": 310,
1724
+ "17": 346,
1725
+ "18": 350,
1726
+ "19": 333,
1727
+ "20": 333
1728
+ },
1729
+ "total": 3365
1730
+ },
1731
+ "movie_festival_awards": {
1732
+ "per_op": {
1733
+ "11": 315,
1734
+ "12": 327,
1735
+ "13": 324,
1736
+ "14": 337,
1737
+ "15": 324,
1738
+ "16": 339,
1739
+ "17": 332,
1740
+ "18": 310,
1741
+ "19": 331,
1742
+ "20": 333
1743
+ },
1744
+ "total": 3272
1745
+ },
1746
+ "teachers_in_school": {
1747
+ "per_op": {
1748
+ "11": 332,
1749
+ "12": 319,
1750
+ "13": 357,
1751
+ "14": 342,
1752
+ "15": 330,
1753
+ "16": 351,
1754
+ "17": 322,
1755
+ "18": 340,
1756
+ "19": 336,
1757
+ "20": 334
1758
+ },
1759
+ "total": 3363
1760
+ }
1761
+ },
1762
+ "total": {
1763
+ "per_op": {
1764
+ "11": 1000,
1765
+ "12": 1000,
1766
+ "13": 1000,
1767
+ "14": 1000,
1768
+ "15": 1000,
1769
+ "16": 1000,
1770
+ "17": 1000,
1771
+ "18": 1000,
1772
+ "19": 1000,
1773
+ "20": 1000
1774
+ },
1775
+ "total": 10000
1776
+ }
1777
+ }
1778
+ }
1779
+ }
1780
+ }