ZachW commited on
Commit
b7bc195
·
verified ·
1 Parent(s): 610329e

Upload extrapolation artifact: 050302 OPD Ref-KL OP13-20 step200 graph aggregate results

Browse files
050302/evals/opd050302_refkl_s200_merged_hf/graph_results/results.json ADDED
@@ -0,0 +1,1780 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "files": {
3
+ "opd050302_refkl_s200_merged_hf_ood_generations.jsonl.graph_results.jsonl": {
4
+ "per_template": {
5
+ "crazy_zootopia": {
6
+ "per_op_pass_at_k": {
7
+ "11": {
8
+ "pass@1": 0.3342776203966006,
9
+ "pass@2": 0.37960339943342775,
10
+ "pass@4": 0.41076487252124644,
11
+ "pass@8": 0.4192634560906516,
12
+ "pass@16": 0.43342776203966005,
13
+ "pass@32": 0.44192634560906513,
14
+ "pass@64": 0.4475920679886686,
15
+ "pass@128": 0.46175637393767704
16
+ },
17
+ "12": {
18
+ "pass@1": 0.4265536723163842,
19
+ "pass@2": 0.4604519774011299,
20
+ "pass@4": 0.4774011299435028,
21
+ "pass@8": 0.4971751412429379,
22
+ "pass@16": 0.5028248587570622,
23
+ "pass@32": 0.5084745762711864,
24
+ "pass@64": 0.519774011299435,
25
+ "pass@128": 0.5225988700564972
26
+ },
27
+ "13": {
28
+ "pass@1": 0.25705329153605017,
29
+ "pass@2": 0.31347962382445144,
30
+ "pass@4": 0.3667711598746082,
31
+ "pass@8": 0.4012539184952978,
32
+ "pass@16": 0.4169278996865204,
33
+ "pass@32": 0.4263322884012539,
34
+ "pass@64": 0.438871473354232,
35
+ "pass@128": 0.4482758620689655
36
+ },
37
+ "14": {
38
+ "pass@1": 0.2118380062305296,
39
+ "pass@2": 0.26479750778816197,
40
+ "pass@4": 0.3177570093457944,
41
+ "pass@8": 0.34890965732087226,
42
+ "pass@16": 0.38317757009345793,
43
+ "pass@32": 0.40186915887850466,
44
+ "pass@64": 0.4174454828660436,
45
+ "pass@128": 0.42679127725856697
46
+ },
47
+ "15": {
48
+ "pass@1": 0.13005780346820808,
49
+ "pass@2": 0.15895953757225434,
50
+ "pass@4": 0.20520231213872833,
51
+ "pass@8": 0.24277456647398843,
52
+ "pass@16": 0.2745664739884393,
53
+ "pass@32": 0.30057803468208094,
54
+ "pass@64": 0.3208092485549133,
55
+ "pass@128": 0.33236994219653176
56
+ },
57
+ "16": {
58
+ "pass@1": 0.11612903225806452,
59
+ "pass@2": 0.15483870967741936,
60
+ "pass@4": 0.2,
61
+ "pass@8": 0.24516129032258063,
62
+ "pass@16": 0.2709677419354839,
63
+ "pass@32": 0.29354838709677417,
64
+ "pass@64": 0.3032258064516129,
65
+ "pass@128": 0.33225806451612905
66
+ },
67
+ "17": {
68
+ "pass@1": 0.046242774566473986,
69
+ "pass@2": 0.08092485549132948,
70
+ "pass@4": 0.12138728323699421,
71
+ "pass@8": 0.14739884393063585,
72
+ "pass@16": 0.18208092485549132,
73
+ "pass@32": 0.21965317919075145,
74
+ "pass@64": 0.23699421965317918,
75
+ "pass@128": 0.2514450867052023
76
+ },
77
+ "18": {
78
+ "pass@1": 0.02857142857142857,
79
+ "pass@2": 0.04285714285714286,
80
+ "pass@4": 0.06571428571428571,
81
+ "pass@8": 0.07428571428571429,
82
+ "pass@16": 0.08857142857142856,
83
+ "pass@32": 0.10857142857142857,
84
+ "pass@64": 0.12,
85
+ "pass@128": 0.13714285714285715
86
+ },
87
+ "19": {
88
+ "pass@1": 0.006006006006006006,
89
+ "pass@2": 0.018018018018018018,
90
+ "pass@4": 0.021021021021021023,
91
+ "pass@8": 0.021021021021021023,
92
+ "pass@16": 0.03003003003003003,
93
+ "pass@32": 0.04504504504504504,
94
+ "pass@64": 0.057057057057057055,
95
+ "pass@128": 0.07207207207207207
96
+ },
97
+ "20": {
98
+ "pass@1": 0.0,
99
+ "pass@2": 0.012012012012012012,
100
+ "pass@4": 0.024024024024024024,
101
+ "pass@8": 0.03003003003003003,
102
+ "pass@16": 0.03303303303303303,
103
+ "pass@32": 0.04504504504504504,
104
+ "pass@64": 0.04804804804804805,
105
+ "pass@128": 0.06306306306306306
106
+ }
107
+ },
108
+ "per_op_pass_at_columns": {
109
+ "pass@1": {
110
+ "11": 0.3342776203966006,
111
+ "12": 0.4265536723163842,
112
+ "13": 0.25705329153605017,
113
+ "14": 0.2118380062305296,
114
+ "15": 0.13005780346820808,
115
+ "16": 0.11612903225806452,
116
+ "17": 0.046242774566473986,
117
+ "18": 0.02857142857142857,
118
+ "19": 0.006006006006006006,
119
+ "20": 0.0
120
+ },
121
+ "pass@2": {
122
+ "11": 0.37960339943342775,
123
+ "12": 0.4604519774011299,
124
+ "13": 0.31347962382445144,
125
+ "14": 0.26479750778816197,
126
+ "15": 0.15895953757225434,
127
+ "16": 0.15483870967741936,
128
+ "17": 0.08092485549132948,
129
+ "18": 0.04285714285714286,
130
+ "19": 0.018018018018018018,
131
+ "20": 0.012012012012012012
132
+ },
133
+ "pass@4": {
134
+ "11": 0.41076487252124644,
135
+ "12": 0.4774011299435028,
136
+ "13": 0.3667711598746082,
137
+ "14": 0.3177570093457944,
138
+ "15": 0.20520231213872833,
139
+ "16": 0.2,
140
+ "17": 0.12138728323699421,
141
+ "18": 0.06571428571428571,
142
+ "19": 0.021021021021021023,
143
+ "20": 0.024024024024024024
144
+ },
145
+ "pass@8": {
146
+ "11": 0.4192634560906516,
147
+ "12": 0.4971751412429379,
148
+ "13": 0.4012539184952978,
149
+ "14": 0.34890965732087226,
150
+ "15": 0.24277456647398843,
151
+ "16": 0.24516129032258063,
152
+ "17": 0.14739884393063585,
153
+ "18": 0.07428571428571429,
154
+ "19": 0.021021021021021023,
155
+ "20": 0.03003003003003003
156
+ },
157
+ "pass@16": {
158
+ "11": 0.43342776203966005,
159
+ "12": 0.5028248587570622,
160
+ "13": 0.4169278996865204,
161
+ "14": 0.38317757009345793,
162
+ "15": 0.2745664739884393,
163
+ "16": 0.2709677419354839,
164
+ "17": 0.18208092485549132,
165
+ "18": 0.08857142857142856,
166
+ "19": 0.03003003003003003,
167
+ "20": 0.03303303303303303
168
+ },
169
+ "pass@32": {
170
+ "11": 0.44192634560906513,
171
+ "12": 0.5084745762711864,
172
+ "13": 0.4263322884012539,
173
+ "14": 0.40186915887850466,
174
+ "15": 0.30057803468208094,
175
+ "16": 0.29354838709677417,
176
+ "17": 0.21965317919075145,
177
+ "18": 0.10857142857142857,
178
+ "19": 0.04504504504504504,
179
+ "20": 0.04504504504504504
180
+ },
181
+ "pass@64": {
182
+ "11": 0.4475920679886686,
183
+ "12": 0.519774011299435,
184
+ "13": 0.438871473354232,
185
+ "14": 0.4174454828660436,
186
+ "15": 0.3208092485549133,
187
+ "16": 0.3032258064516129,
188
+ "17": 0.23699421965317918,
189
+ "18": 0.12,
190
+ "19": 0.057057057057057055,
191
+ "20": 0.04804804804804805
192
+ },
193
+ "pass@128": {
194
+ "11": 0.46175637393767704,
195
+ "12": 0.5225988700564972,
196
+ "13": 0.4482758620689655,
197
+ "14": 0.42679127725856697,
198
+ "15": 0.33236994219653176,
199
+ "16": 0.33225806451612905,
200
+ "17": 0.2514450867052023,
201
+ "18": 0.13714285714285715,
202
+ "19": 0.07207207207207207,
203
+ "20": 0.06306306306306306
204
+ }
205
+ },
206
+ "total_pass_at_k": {
207
+ "pass@1": 0.15690936106983655,
208
+ "pass@2": 0.18959881129271916,
209
+ "pass@4": 0.22169390787518573,
210
+ "pass@8": 0.24309063893016344,
211
+ "pass@16": 0.26181277860326896,
212
+ "pass@32": 0.27934621099554235,
213
+ "pass@64": 0.2912332838038633,
214
+ "pass@128": 0.3049034175334324
215
+ }
216
+ },
217
+ "movie_festival_awards": {
218
+ "per_op_pass_at_k": {
219
+ "11": {
220
+ "pass@1": 0.37142857142857144,
221
+ "pass@2": 0.4095238095238095,
222
+ "pass@4": 0.4253968253968254,
223
+ "pass@8": 0.45396825396825397,
224
+ "pass@16": 0.473015873015873,
225
+ "pass@32": 0.4793650793650794,
226
+ "pass@64": 0.49206349206349204,
227
+ "pass@128": 0.5047619047619047
228
+ },
229
+ "12": {
230
+ "pass@1": 0.40061162079510704,
231
+ "pass@2": 0.43730886850152906,
232
+ "pass@4": 0.46788990825688076,
233
+ "pass@8": 0.4801223241590214,
234
+ "pass@16": 0.4954128440366973,
235
+ "pass@32": 0.5107033639143731,
236
+ "pass@64": 0.5198776758409785,
237
+ "pass@128": 0.5351681957186545
238
+ },
239
+ "13": {
240
+ "pass@1": 0.27469135802469136,
241
+ "pass@2": 0.3487654320987654,
242
+ "pass@4": 0.3888888888888889,
243
+ "pass@8": 0.4104938271604938,
244
+ "pass@16": 0.43209876543209874,
245
+ "pass@32": 0.4444444444444444,
246
+ "pass@64": 0.4537037037037037,
247
+ "pass@128": 0.46296296296296297
248
+ },
249
+ "14": {
250
+ "pass@1": 0.1572700296735905,
251
+ "pass@2": 0.21364985163204747,
252
+ "pass@4": 0.2433234421364985,
253
+ "pass@8": 0.28486646884273,
254
+ "pass@16": 0.3056379821958457,
255
+ "pass@32": 0.34421364985163205,
256
+ "pass@64": 0.3649851632047478,
257
+ "pass@128": 0.3827893175074184
258
+ },
259
+ "15": {
260
+ "pass@1": 0.13271604938271606,
261
+ "pass@2": 0.1728395061728395,
262
+ "pass@4": 0.2006172839506173,
263
+ "pass@8": 0.2345679012345679,
264
+ "pass@16": 0.25617283950617287,
265
+ "pass@32": 0.2962962962962963,
266
+ "pass@64": 0.3148148148148148,
267
+ "pass@128": 0.32098765432098764
268
+ },
269
+ "16": {
270
+ "pass@1": 0.09734513274336283,
271
+ "pass@2": 0.11799410029498525,
272
+ "pass@4": 0.16519174041297935,
273
+ "pass@8": 0.22123893805309736,
274
+ "pass@16": 0.24778761061946902,
275
+ "pass@32": 0.2743362831858407,
276
+ "pass@64": 0.2949852507374631,
277
+ "pass@128": 0.336283185840708
278
+ },
279
+ "17": {
280
+ "pass@1": 0.02710843373493976,
281
+ "pass@2": 0.045180722891566265,
282
+ "pass@4": 0.07228915662650602,
283
+ "pass@8": 0.0963855421686747,
284
+ "pass@16": 0.12048192771084337,
285
+ "pass@32": 0.14759036144578314,
286
+ "pass@64": 0.18674698795180722,
287
+ "pass@128": 0.21084337349397592
288
+ },
289
+ "18": {
290
+ "pass@1": 0.03225806451612903,
291
+ "pass@2": 0.041935483870967745,
292
+ "pass@4": 0.06129032258064516,
293
+ "pass@8": 0.08709677419354839,
294
+ "pass@16": 0.0967741935483871,
295
+ "pass@32": 0.11290322580645161,
296
+ "pass@64": 0.13225806451612904,
297
+ "pass@128": 0.14193548387096774
298
+ },
299
+ "19": {
300
+ "pass@1": 0.006042296072507553,
301
+ "pass@2": 0.006042296072507553,
302
+ "pass@4": 0.012084592145015106,
303
+ "pass@8": 0.021148036253776436,
304
+ "pass@16": 0.02416918429003021,
305
+ "pass@32": 0.030211480362537766,
306
+ "pass@64": 0.045317220543806644,
307
+ "pass@128": 0.0634441087613293
308
+ },
309
+ "20": {
310
+ "pass@1": 0.003003003003003003,
311
+ "pass@2": 0.003003003003003003,
312
+ "pass@4": 0.003003003003003003,
313
+ "pass@8": 0.009009009009009009,
314
+ "pass@16": 0.009009009009009009,
315
+ "pass@32": 0.021021021021021023,
316
+ "pass@64": 0.024024024024024024,
317
+ "pass@128": 0.03303303303303303
318
+ }
319
+ },
320
+ "per_op_pass_at_columns": {
321
+ "pass@1": {
322
+ "11": 0.37142857142857144,
323
+ "12": 0.40061162079510704,
324
+ "13": 0.27469135802469136,
325
+ "14": 0.1572700296735905,
326
+ "15": 0.13271604938271606,
327
+ "16": 0.09734513274336283,
328
+ "17": 0.02710843373493976,
329
+ "18": 0.03225806451612903,
330
+ "19": 0.006042296072507553,
331
+ "20": 0.003003003003003003
332
+ },
333
+ "pass@2": {
334
+ "11": 0.4095238095238095,
335
+ "12": 0.43730886850152906,
336
+ "13": 0.3487654320987654,
337
+ "14": 0.21364985163204747,
338
+ "15": 0.1728395061728395,
339
+ "16": 0.11799410029498525,
340
+ "17": 0.045180722891566265,
341
+ "18": 0.041935483870967745,
342
+ "19": 0.006042296072507553,
343
+ "20": 0.003003003003003003
344
+ },
345
+ "pass@4": {
346
+ "11": 0.4253968253968254,
347
+ "12": 0.46788990825688076,
348
+ "13": 0.3888888888888889,
349
+ "14": 0.2433234421364985,
350
+ "15": 0.2006172839506173,
351
+ "16": 0.16519174041297935,
352
+ "17": 0.07228915662650602,
353
+ "18": 0.06129032258064516,
354
+ "19": 0.012084592145015106,
355
+ "20": 0.003003003003003003
356
+ },
357
+ "pass@8": {
358
+ "11": 0.45396825396825397,
359
+ "12": 0.4801223241590214,
360
+ "13": 0.4104938271604938,
361
+ "14": 0.28486646884273,
362
+ "15": 0.2345679012345679,
363
+ "16": 0.22123893805309736,
364
+ "17": 0.0963855421686747,
365
+ "18": 0.08709677419354839,
366
+ "19": 0.021148036253776436,
367
+ "20": 0.009009009009009009
368
+ },
369
+ "pass@16": {
370
+ "11": 0.473015873015873,
371
+ "12": 0.4954128440366973,
372
+ "13": 0.43209876543209874,
373
+ "14": 0.3056379821958457,
374
+ "15": 0.25617283950617287,
375
+ "16": 0.24778761061946902,
376
+ "17": 0.12048192771084337,
377
+ "18": 0.0967741935483871,
378
+ "19": 0.02416918429003021,
379
+ "20": 0.009009009009009009
380
+ },
381
+ "pass@32": {
382
+ "11": 0.4793650793650794,
383
+ "12": 0.5107033639143731,
384
+ "13": 0.4444444444444444,
385
+ "14": 0.34421364985163205,
386
+ "15": 0.2962962962962963,
387
+ "16": 0.2743362831858407,
388
+ "17": 0.14759036144578314,
389
+ "18": 0.11290322580645161,
390
+ "19": 0.030211480362537766,
391
+ "20": 0.021021021021021023
392
+ },
393
+ "pass@64": {
394
+ "11": 0.49206349206349204,
395
+ "12": 0.5198776758409785,
396
+ "13": 0.4537037037037037,
397
+ "14": 0.3649851632047478,
398
+ "15": 0.3148148148148148,
399
+ "16": 0.2949852507374631,
400
+ "17": 0.18674698795180722,
401
+ "18": 0.13225806451612904,
402
+ "19": 0.045317220543806644,
403
+ "20": 0.024024024024024024
404
+ },
405
+ "pass@128": {
406
+ "11": 0.5047619047619047,
407
+ "12": 0.5351681957186545,
408
+ "13": 0.46296296296296297,
409
+ "14": 0.3827893175074184,
410
+ "15": 0.32098765432098764,
411
+ "16": 0.336283185840708,
412
+ "17": 0.21084337349397592,
413
+ "18": 0.14193548387096774,
414
+ "19": 0.0634441087613293,
415
+ "20": 0.03303303303303303
416
+ }
417
+ },
418
+ "total_pass_at_k": {
419
+ "pass@1": 0.1491442542787286,
420
+ "pass@2": 0.1784841075794621,
421
+ "pass@4": 0.20293398533007334,
422
+ "pass@8": 0.2289119804400978,
423
+ "pass@16": 0.24511002444987776,
424
+ "pass@32": 0.265281173594132,
425
+ "pass@64": 0.2820904645476773,
426
+ "pass@128": 0.2985941320293399
427
+ }
428
+ },
429
+ "teachers_in_school": {
430
+ "per_op_pass_at_k": {
431
+ "11": {
432
+ "pass@1": 0.45180722891566266,
433
+ "pass@2": 0.49096385542168675,
434
+ "pass@4": 0.5,
435
+ "pass@8": 0.5240963855421686,
436
+ "pass@16": 0.5421686746987951,
437
+ "pass@32": 0.5572289156626506,
438
+ "pass@64": 0.5632530120481928,
439
+ "pass@128": 0.5662650602409639
440
+ },
441
+ "12": {
442
+ "pass@1": 0.3385579937304075,
443
+ "pass@2": 0.3793103448275862,
444
+ "pass@4": 0.3949843260188088,
445
+ "pass@8": 0.4169278996865204,
446
+ "pass@16": 0.43260188087774293,
447
+ "pass@32": 0.438871473354232,
448
+ "pass@64": 0.45454545454545453,
449
+ "pass@128": 0.4608150470219436
450
+ },
451
+ "13": {
452
+ "pass@1": 0.2857142857142857,
453
+ "pass@2": 0.33053221288515405,
454
+ "pass@4": 0.3641456582633053,
455
+ "pass@8": 0.39775910364145656,
456
+ "pass@16": 0.40896358543417366,
457
+ "pass@32": 0.4341736694677871,
458
+ "pass@64": 0.4481792717086835,
459
+ "pass@128": 0.45938375350140054
460
+ },
461
+ "14": {
462
+ "pass@1": 0.2222222222222222,
463
+ "pass@2": 0.2719298245614035,
464
+ "pass@4": 0.3216374269005848,
465
+ "pass@8": 0.34502923976608185,
466
+ "pass@16": 0.3684210526315789,
467
+ "pass@32": 0.3830409356725146,
468
+ "pass@64": 0.40350877192982454,
469
+ "pass@128": 0.4269005847953216
470
+ },
471
+ "15": {
472
+ "pass@1": 0.12424242424242424,
473
+ "pass@2": 0.1696969696969697,
474
+ "pass@4": 0.21515151515151515,
475
+ "pass@8": 0.26666666666666666,
476
+ "pass@16": 0.3,
477
+ "pass@32": 0.3090909090909091,
478
+ "pass@64": 0.3333333333333333,
479
+ "pass@128": 0.3575757575757576
480
+ },
481
+ "16": {
482
+ "pass@1": 0.12535612535612536,
483
+ "pass@2": 0.1737891737891738,
484
+ "pass@4": 0.21652421652421652,
485
+ "pass@8": 0.23076923076923078,
486
+ "pass@16": 0.2621082621082621,
487
+ "pass@32": 0.2962962962962963,
488
+ "pass@64": 0.32763532763532766,
489
+ "pass@128": 0.3418803418803419
490
+ },
491
+ "17": {
492
+ "pass@1": 0.040372670807453416,
493
+ "pass@2": 0.07763975155279502,
494
+ "pass@4": 0.09316770186335403,
495
+ "pass@8": 0.13664596273291926,
496
+ "pass@16": 0.17080745341614906,
497
+ "pass@32": 0.19254658385093168,
498
+ "pass@64": 0.20186335403726707,
499
+ "pass@128": 0.2329192546583851
500
+ },
501
+ "18": {
502
+ "pass@1": 0.05,
503
+ "pass@2": 0.06470588235294118,
504
+ "pass@4": 0.08235294117647059,
505
+ "pass@8": 0.09705882352941177,
506
+ "pass@16": 0.11470588235294117,
507
+ "pass@32": 0.13823529411764707,
508
+ "pass@64": 0.1588235294117647,
509
+ "pass@128": 0.17352941176470588
510
+ },
511
+ "19": {
512
+ "pass@1": 0.005952380952380952,
513
+ "pass@2": 0.011904761904761904,
514
+ "pass@4": 0.020833333333333332,
515
+ "pass@8": 0.03869047619047619,
516
+ "pass@16": 0.050595238095238096,
517
+ "pass@32": 0.06547619047619048,
518
+ "pass@64": 0.07738095238095238,
519
+ "pass@128": 0.07738095238095238
520
+ },
521
+ "20": {
522
+ "pass@1": 0.0029940119760479044,
523
+ "pass@2": 0.0029940119760479044,
524
+ "pass@4": 0.005988023952095809,
525
+ "pass@8": 0.008982035928143712,
526
+ "pass@16": 0.011976047904191617,
527
+ "pass@32": 0.023952095808383235,
528
+ "pass@64": 0.03293413173652695,
529
+ "pass@128": 0.03592814371257485
530
+ }
531
+ },
532
+ "per_op_pass_at_columns": {
533
+ "pass@1": {
534
+ "11": 0.45180722891566266,
535
+ "12": 0.3385579937304075,
536
+ "13": 0.2857142857142857,
537
+ "14": 0.2222222222222222,
538
+ "15": 0.12424242424242424,
539
+ "16": 0.12535612535612536,
540
+ "17": 0.040372670807453416,
541
+ "18": 0.05,
542
+ "19": 0.005952380952380952,
543
+ "20": 0.0029940119760479044
544
+ },
545
+ "pass@2": {
546
+ "11": 0.49096385542168675,
547
+ "12": 0.3793103448275862,
548
+ "13": 0.33053221288515405,
549
+ "14": 0.2719298245614035,
550
+ "15": 0.1696969696969697,
551
+ "16": 0.1737891737891738,
552
+ "17": 0.07763975155279502,
553
+ "18": 0.06470588235294118,
554
+ "19": 0.011904761904761904,
555
+ "20": 0.0029940119760479044
556
+ },
557
+ "pass@4": {
558
+ "11": 0.5,
559
+ "12": 0.3949843260188088,
560
+ "13": 0.3641456582633053,
561
+ "14": 0.3216374269005848,
562
+ "15": 0.21515151515151515,
563
+ "16": 0.21652421652421652,
564
+ "17": 0.09316770186335403,
565
+ "18": 0.08235294117647059,
566
+ "19": 0.020833333333333332,
567
+ "20": 0.005988023952095809
568
+ },
569
+ "pass@8": {
570
+ "11": 0.5240963855421686,
571
+ "12": 0.4169278996865204,
572
+ "13": 0.39775910364145656,
573
+ "14": 0.34502923976608185,
574
+ "15": 0.26666666666666666,
575
+ "16": 0.23076923076923078,
576
+ "17": 0.13664596273291926,
577
+ "18": 0.09705882352941177,
578
+ "19": 0.03869047619047619,
579
+ "20": 0.008982035928143712
580
+ },
581
+ "pass@16": {
582
+ "11": 0.5421686746987951,
583
+ "12": 0.43260188087774293,
584
+ "13": 0.40896358543417366,
585
+ "14": 0.3684210526315789,
586
+ "15": 0.3,
587
+ "16": 0.2621082621082621,
588
+ "17": 0.17080745341614906,
589
+ "18": 0.11470588235294117,
590
+ "19": 0.050595238095238096,
591
+ "20": 0.011976047904191617
592
+ },
593
+ "pass@32": {
594
+ "11": 0.5572289156626506,
595
+ "12": 0.438871473354232,
596
+ "13": 0.4341736694677871,
597
+ "14": 0.3830409356725146,
598
+ "15": 0.3090909090909091,
599
+ "16": 0.2962962962962963,
600
+ "17": 0.19254658385093168,
601
+ "18": 0.13823529411764707,
602
+ "19": 0.06547619047619048,
603
+ "20": 0.023952095808383235
604
+ },
605
+ "pass@64": {
606
+ "11": 0.5632530120481928,
607
+ "12": 0.45454545454545453,
608
+ "13": 0.4481792717086835,
609
+ "14": 0.40350877192982454,
610
+ "15": 0.3333333333333333,
611
+ "16": 0.32763532763532766,
612
+ "17": 0.20186335403726707,
613
+ "18": 0.1588235294117647,
614
+ "19": 0.07738095238095238,
615
+ "20": 0.03293413173652695
616
+ },
617
+ "pass@128": {
618
+ "11": 0.5662650602409639,
619
+ "12": 0.4608150470219436,
620
+ "13": 0.45938375350140054,
621
+ "14": 0.4269005847953216,
622
+ "15": 0.3575757575757576,
623
+ "16": 0.3418803418803419,
624
+ "17": 0.2329192546583851,
625
+ "18": 0.17352941176470588,
626
+ "19": 0.07738095238095238,
627
+ "20": 0.03592814371257485
628
+ }
629
+ },
630
+ "total_pass_at_k": {
631
+ "pass@1": 0.1647338685697294,
632
+ "pass@2": 0.1974427594409753,
633
+ "pass@4": 0.22182575081772227,
634
+ "pass@8": 0.24650609574784418,
635
+ "pass@16": 0.2664287838239667,
636
+ "pass@32": 0.2842699970264645,
637
+ "pass@64": 0.3006244424620874,
638
+ "pass@128": 0.3137079988105858
639
+ }
640
+ }
641
+ },
642
+ "total": {
643
+ "per_op_pass_at_k": {
644
+ "11": {
645
+ "pass@1": 0.385,
646
+ "pass@2": 0.426,
647
+ "pass@4": 0.445,
648
+ "pass@8": 0.465,
649
+ "pass@16": 0.482,
650
+ "pass@32": 0.492,
651
+ "pass@64": 0.5,
652
+ "pass@128": 0.51
653
+ },
654
+ "12": {
655
+ "pass@1": 0.39,
656
+ "pass@2": 0.427,
657
+ "pass@4": 0.448,
658
+ "pass@8": 0.466,
659
+ "pass@16": 0.478,
660
+ "pass@32": 0.487,
661
+ "pass@64": 0.499,
662
+ "pass@128": 0.507
663
+ },
664
+ "13": {
665
+ "pass@1": 0.273,
666
+ "pass@2": 0.331,
667
+ "pass@4": 0.373,
668
+ "pass@8": 0.403,
669
+ "pass@16": 0.419,
670
+ "pass@32": 0.435,
671
+ "pass@64": 0.447,
672
+ "pass@128": 0.457
673
+ },
674
+ "14": {
675
+ "pass@1": 0.197,
676
+ "pass@2": 0.25,
677
+ "pass@4": 0.294,
678
+ "pass@8": 0.326,
679
+ "pass@16": 0.352,
680
+ "pass@32": 0.376,
681
+ "pass@64": 0.395,
682
+ "pass@128": 0.412
683
+ },
684
+ "15": {
685
+ "pass@1": 0.129,
686
+ "pass@2": 0.167,
687
+ "pass@4": 0.207,
688
+ "pass@8": 0.248,
689
+ "pass@16": 0.277,
690
+ "pass@32": 0.302,
691
+ "pass@64": 0.323,
692
+ "pass@128": 0.337
693
+ },
694
+ "16": {
695
+ "pass@1": 0.113,
696
+ "pass@2": 0.149,
697
+ "pass@4": 0.194,
698
+ "pass@8": 0.232,
699
+ "pass@16": 0.26,
700
+ "pass@32": 0.288,
701
+ "pass@64": 0.309,
702
+ "pass@128": 0.337
703
+ },
704
+ "17": {
705
+ "pass@1": 0.038,
706
+ "pass@2": 0.068,
707
+ "pass@4": 0.096,
708
+ "pass@8": 0.127,
709
+ "pass@16": 0.158,
710
+ "pass@32": 0.187,
711
+ "pass@64": 0.209,
712
+ "pass@128": 0.232
713
+ },
714
+ "18": {
715
+ "pass@1": 0.037,
716
+ "pass@2": 0.05,
717
+ "pass@4": 0.07,
718
+ "pass@8": 0.086,
719
+ "pass@16": 0.1,
720
+ "pass@32": 0.12,
721
+ "pass@64": 0.137,
722
+ "pass@128": 0.151
723
+ },
724
+ "19": {
725
+ "pass@1": 0.006,
726
+ "pass@2": 0.012,
727
+ "pass@4": 0.018,
728
+ "pass@8": 0.027,
729
+ "pass@16": 0.035,
730
+ "pass@32": 0.047,
731
+ "pass@64": 0.06,
732
+ "pass@128": 0.071
733
+ },
734
+ "20": {
735
+ "pass@1": 0.002,
736
+ "pass@2": 0.006,
737
+ "pass@4": 0.011,
738
+ "pass@8": 0.016,
739
+ "pass@16": 0.018,
740
+ "pass@32": 0.03,
741
+ "pass@64": 0.035,
742
+ "pass@128": 0.044
743
+ }
744
+ },
745
+ "per_op_pass_at_columns": {
746
+ "pass@1": {
747
+ "11": 0.385,
748
+ "12": 0.39,
749
+ "13": 0.273,
750
+ "14": 0.197,
751
+ "15": 0.129,
752
+ "16": 0.113,
753
+ "17": 0.038,
754
+ "18": 0.037,
755
+ "19": 0.006,
756
+ "20": 0.002
757
+ },
758
+ "pass@2": {
759
+ "11": 0.426,
760
+ "12": 0.427,
761
+ "13": 0.331,
762
+ "14": 0.25,
763
+ "15": 0.167,
764
+ "16": 0.149,
765
+ "17": 0.068,
766
+ "18": 0.05,
767
+ "19": 0.012,
768
+ "20": 0.006
769
+ },
770
+ "pass@4": {
771
+ "11": 0.445,
772
+ "12": 0.448,
773
+ "13": 0.373,
774
+ "14": 0.294,
775
+ "15": 0.207,
776
+ "16": 0.194,
777
+ "17": 0.096,
778
+ "18": 0.07,
779
+ "19": 0.018,
780
+ "20": 0.011
781
+ },
782
+ "pass@8": {
783
+ "11": 0.465,
784
+ "12": 0.466,
785
+ "13": 0.403,
786
+ "14": 0.326,
787
+ "15": 0.248,
788
+ "16": 0.232,
789
+ "17": 0.127,
790
+ "18": 0.086,
791
+ "19": 0.027,
792
+ "20": 0.016
793
+ },
794
+ "pass@16": {
795
+ "11": 0.482,
796
+ "12": 0.478,
797
+ "13": 0.419,
798
+ "14": 0.352,
799
+ "15": 0.277,
800
+ "16": 0.26,
801
+ "17": 0.158,
802
+ "18": 0.1,
803
+ "19": 0.035,
804
+ "20": 0.018
805
+ },
806
+ "pass@32": {
807
+ "11": 0.492,
808
+ "12": 0.487,
809
+ "13": 0.435,
810
+ "14": 0.376,
811
+ "15": 0.302,
812
+ "16": 0.288,
813
+ "17": 0.187,
814
+ "18": 0.12,
815
+ "19": 0.047,
816
+ "20": 0.03
817
+ },
818
+ "pass@64": {
819
+ "11": 0.5,
820
+ "12": 0.499,
821
+ "13": 0.447,
822
+ "14": 0.395,
823
+ "15": 0.323,
824
+ "16": 0.309,
825
+ "17": 0.209,
826
+ "18": 0.137,
827
+ "19": 0.06,
828
+ "20": 0.035
829
+ },
830
+ "pass@128": {
831
+ "11": 0.51,
832
+ "12": 0.507,
833
+ "13": 0.457,
834
+ "14": 0.412,
835
+ "15": 0.337,
836
+ "16": 0.337,
837
+ "17": 0.232,
838
+ "18": 0.151,
839
+ "19": 0.071,
840
+ "20": 0.044
841
+ }
842
+ },
843
+ "total_pass_at_k": {
844
+ "pass@1": 0.157,
845
+ "pass@2": 0.1886,
846
+ "pass@4": 0.2156,
847
+ "pass@8": 0.2396,
848
+ "pass@16": 0.2579,
849
+ "pass@32": 0.2764,
850
+ "pass@64": 0.2914,
851
+ "pass@128": 0.3058
852
+ }
853
+ },
854
+ "ks": [
855
+ 1,
856
+ 2,
857
+ 4,
858
+ 8,
859
+ 16,
860
+ 32,
861
+ 64,
862
+ 128
863
+ ],
864
+ "prompt_counts": {
865
+ "per_template": {
866
+ "crazy_zootopia": {
867
+ "per_op": {
868
+ "11": 353,
869
+ "12": 354,
870
+ "13": 319,
871
+ "14": 321,
872
+ "15": 346,
873
+ "16": 310,
874
+ "17": 346,
875
+ "18": 350,
876
+ "19": 333,
877
+ "20": 333
878
+ },
879
+ "total": 3365
880
+ },
881
+ "movie_festival_awards": {
882
+ "per_op": {
883
+ "11": 315,
884
+ "12": 327,
885
+ "13": 324,
886
+ "14": 337,
887
+ "15": 324,
888
+ "16": 339,
889
+ "17": 332,
890
+ "18": 310,
891
+ "19": 331,
892
+ "20": 333
893
+ },
894
+ "total": 3272
895
+ },
896
+ "teachers_in_school": {
897
+ "per_op": {
898
+ "11": 332,
899
+ "12": 319,
900
+ "13": 357,
901
+ "14": 342,
902
+ "15": 330,
903
+ "16": 351,
904
+ "17": 322,
905
+ "18": 340,
906
+ "19": 336,
907
+ "20": 334
908
+ },
909
+ "total": 3363
910
+ }
911
+ },
912
+ "total": {
913
+ "per_op": {
914
+ "11": 1000,
915
+ "12": 1000,
916
+ "13": 1000,
917
+ "14": 1000,
918
+ "15": 1000,
919
+ "16": 1000,
920
+ "17": 1000,
921
+ "18": 1000,
922
+ "19": 1000,
923
+ "20": 1000
924
+ },
925
+ "total": 10000
926
+ }
927
+ }
928
+ },
929
+ "opd050302_refkl_s200_merged_hf_id_generations.jsonl.graph_results.jsonl": {
930
+ "per_template": {
931
+ "crazy_zootopia": {
932
+ "per_op_pass_at_k": {
933
+ "2": {
934
+ "pass@1": 0.9065420560747663,
935
+ "pass@2": 0.9501557632398754,
936
+ "pass@4": 0.9626168224299065,
937
+ "pass@8": 0.9657320872274143,
938
+ "pass@16": 0.9813084112149533,
939
+ "pass@32": 0.9844236760124611,
940
+ "pass@64": 0.9844236760124611,
941
+ "pass@128": 0.9875389408099688
942
+ },
943
+ "3": {
944
+ "pass@1": 0.8440366972477065,
945
+ "pass@2": 0.8776758409785933,
946
+ "pass@4": 0.8960244648318043,
947
+ "pass@8": 0.9174311926605505,
948
+ "pass@16": 0.9388379204892966,
949
+ "pass@32": 0.9510703363914373,
950
+ "pass@64": 0.9571865443425076,
951
+ "pass@128": 0.9663608562691132
952
+ },
953
+ "4": {
954
+ "pass@1": 0.66875,
955
+ "pass@2": 0.690625,
956
+ "pass@4": 0.7,
957
+ "pass@8": 0.709375,
958
+ "pass@16": 0.734375,
959
+ "pass@32": 0.740625,
960
+ "pass@64": 0.75625,
961
+ "pass@128": 0.775
962
+ },
963
+ "5": {
964
+ "pass@1": 0.5428571428571428,
965
+ "pass@2": 0.580952380952381,
966
+ "pass@4": 0.5968253968253968,
967
+ "pass@8": 0.6317460317460317,
968
+ "pass@16": 0.6444444444444445,
969
+ "pass@32": 0.6571428571428571,
970
+ "pass@64": 0.6698412698412698,
971
+ "pass@128": 0.6952380952380952
972
+ },
973
+ "6": {
974
+ "pass@1": 0.5029940119760479,
975
+ "pass@2": 0.5419161676646707,
976
+ "pass@4": 0.562874251497006,
977
+ "pass@8": 0.5808383233532934,
978
+ "pass@16": 0.6077844311377245,
979
+ "pass@32": 0.6287425149700598,
980
+ "pass@64": 0.6497005988023952,
981
+ "pass@128": 0.6826347305389222
982
+ },
983
+ "7": {
984
+ "pass@1": 0.4881656804733728,
985
+ "pass@2": 0.5088757396449705,
986
+ "pass@4": 0.5355029585798816,
987
+ "pass@8": 0.5591715976331361,
988
+ "pass@16": 0.5769230769230769,
989
+ "pass@32": 0.5946745562130178,
990
+ "pass@64": 0.621301775147929,
991
+ "pass@128": 0.6331360946745562
992
+ },
993
+ "8": {
994
+ "pass@1": 0.4423076923076923,
995
+ "pass@2": 0.47435897435897434,
996
+ "pass@4": 0.49038461538461536,
997
+ "pass@8": 0.5128205128205128,
998
+ "pass@16": 0.5256410256410257,
999
+ "pass@32": 0.532051282051282,
1000
+ "pass@64": 0.5480769230769231,
1001
+ "pass@128": 0.5608974358974359
1002
+ },
1003
+ "9": {
1004
+ "pass@1": 0.428169014084507,
1005
+ "pass@2": 0.4704225352112676,
1006
+ "pass@4": 0.5070422535211268,
1007
+ "pass@8": 0.5267605633802817,
1008
+ "pass@16": 0.5521126760563381,
1009
+ "pass@32": 0.571830985915493,
1010
+ "pass@64": 0.5915492957746479,
1011
+ "pass@128": 0.5971830985915493
1012
+ },
1013
+ "10": {
1014
+ "pass@1": 0.4778761061946903,
1015
+ "pass@2": 0.4837758112094395,
1016
+ "pass@4": 0.5014749262536873,
1017
+ "pass@8": 0.5103244837758112,
1018
+ "pass@16": 0.5191740412979351,
1019
+ "pass@32": 0.5221238938053098,
1020
+ "pass@64": 0.5339233038348082,
1021
+ "pass@128": 0.5398230088495575
1022
+ }
1023
+ },
1024
+ "per_op_pass_at_columns": {
1025
+ "pass@1": {
1026
+ "2": 0.9065420560747663,
1027
+ "3": 0.8440366972477065,
1028
+ "4": 0.66875,
1029
+ "5": 0.5428571428571428,
1030
+ "6": 0.5029940119760479,
1031
+ "7": 0.4881656804733728,
1032
+ "8": 0.4423076923076923,
1033
+ "9": 0.428169014084507,
1034
+ "10": 0.4778761061946903
1035
+ },
1036
+ "pass@2": {
1037
+ "2": 0.9501557632398754,
1038
+ "3": 0.8776758409785933,
1039
+ "4": 0.690625,
1040
+ "5": 0.580952380952381,
1041
+ "6": 0.5419161676646707,
1042
+ "7": 0.5088757396449705,
1043
+ "8": 0.47435897435897434,
1044
+ "9": 0.4704225352112676,
1045
+ "10": 0.4837758112094395
1046
+ },
1047
+ "pass@4": {
1048
+ "2": 0.9626168224299065,
1049
+ "3": 0.8960244648318043,
1050
+ "4": 0.7,
1051
+ "5": 0.5968253968253968,
1052
+ "6": 0.562874251497006,
1053
+ "7": 0.5355029585798816,
1054
+ "8": 0.49038461538461536,
1055
+ "9": 0.5070422535211268,
1056
+ "10": 0.5014749262536873
1057
+ },
1058
+ "pass@8": {
1059
+ "2": 0.9657320872274143,
1060
+ "3": 0.9174311926605505,
1061
+ "4": 0.709375,
1062
+ "5": 0.6317460317460317,
1063
+ "6": 0.5808383233532934,
1064
+ "7": 0.5591715976331361,
1065
+ "8": 0.5128205128205128,
1066
+ "9": 0.5267605633802817,
1067
+ "10": 0.5103244837758112
1068
+ },
1069
+ "pass@16": {
1070
+ "2": 0.9813084112149533,
1071
+ "3": 0.9388379204892966,
1072
+ "4": 0.734375,
1073
+ "5": 0.6444444444444445,
1074
+ "6": 0.6077844311377245,
1075
+ "7": 0.5769230769230769,
1076
+ "8": 0.5256410256410257,
1077
+ "9": 0.5521126760563381,
1078
+ "10": 0.5191740412979351
1079
+ },
1080
+ "pass@32": {
1081
+ "2": 0.9844236760124611,
1082
+ "3": 0.9510703363914373,
1083
+ "4": 0.740625,
1084
+ "5": 0.6571428571428571,
1085
+ "6": 0.6287425149700598,
1086
+ "7": 0.5946745562130178,
1087
+ "8": 0.532051282051282,
1088
+ "9": 0.571830985915493,
1089
+ "10": 0.5221238938053098
1090
+ },
1091
+ "pass@64": {
1092
+ "2": 0.9844236760124611,
1093
+ "3": 0.9571865443425076,
1094
+ "4": 0.75625,
1095
+ "5": 0.6698412698412698,
1096
+ "6": 0.6497005988023952,
1097
+ "7": 0.621301775147929,
1098
+ "8": 0.5480769230769231,
1099
+ "9": 0.5915492957746479,
1100
+ "10": 0.5339233038348082
1101
+ },
1102
+ "pass@128": {
1103
+ "2": 0.9875389408099688,
1104
+ "3": 0.9663608562691132,
1105
+ "4": 0.775,
1106
+ "5": 0.6952380952380952,
1107
+ "6": 0.6826347305389222,
1108
+ "7": 0.6331360946745562,
1109
+ "8": 0.5608974358974359,
1110
+ "9": 0.5971830985915493,
1111
+ "10": 0.5398230088495575
1112
+ }
1113
+ },
1114
+ "total_pass_at_k": {
1115
+ "pass@1": 0.5866261398176292,
1116
+ "pass@2": 0.6173590003377237,
1117
+ "pass@4": 0.6369469773725093,
1118
+ "pass@8": 0.6548463356973995,
1119
+ "pass@16": 0.6734211415062479,
1120
+ "pass@32": 0.684903748733536,
1121
+ "pass@64": 0.6994258696386356,
1122
+ "pass@128": 0.713272543059777
1123
+ }
1124
+ },
1125
+ "movie_festival_awards": {
1126
+ "per_op_pass_at_k": {
1127
+ "2": {
1128
+ "pass@1": 0.8857142857142857,
1129
+ "pass@2": 0.9171428571428571,
1130
+ "pass@4": 0.9314285714285714,
1131
+ "pass@8": 0.9514285714285714,
1132
+ "pass@16": 0.9657142857142857,
1133
+ "pass@32": 0.9685714285714285,
1134
+ "pass@64": 0.98,
1135
+ "pass@128": 0.9885714285714285
1136
+ },
1137
+ "3": {
1138
+ "pass@1": 0.880466472303207,
1139
+ "pass@2": 0.9037900874635568,
1140
+ "pass@4": 0.9212827988338192,
1141
+ "pass@8": 0.9358600583090378,
1142
+ "pass@16": 0.9416909620991254,
1143
+ "pass@32": 0.9533527696793003,
1144
+ "pass@64": 0.967930029154519,
1145
+ "pass@128": 0.9708454810495627
1146
+ },
1147
+ "4": {
1148
+ "pass@1": 0.6754385964912281,
1149
+ "pass@2": 0.7134502923976608,
1150
+ "pass@4": 0.7339181286549707,
1151
+ "pass@8": 0.7456140350877193,
1152
+ "pass@16": 0.7602339181286549,
1153
+ "pass@32": 0.7748538011695907,
1154
+ "pass@64": 0.804093567251462,
1155
+ "pass@128": 0.8099415204678363
1156
+ },
1157
+ "5": {
1158
+ "pass@1": 0.5294117647058824,
1159
+ "pass@2": 0.5676470588235294,
1160
+ "pass@4": 0.611764705882353,
1161
+ "pass@8": 0.6294117647058823,
1162
+ "pass@16": 0.6529411764705882,
1163
+ "pass@32": 0.6588235294117647,
1164
+ "pass@64": 0.6735294117647059,
1165
+ "pass@128": 0.6911764705882353
1166
+ },
1167
+ "6": {
1168
+ "pass@1": 0.48580441640378547,
1169
+ "pass@2": 0.5236593059936908,
1170
+ "pass@4": 0.5488958990536278,
1171
+ "pass@8": 0.580441640378549,
1172
+ "pass@16": 0.6056782334384858,
1173
+ "pass@32": 0.6214511041009464,
1174
+ "pass@64": 0.6466876971608833,
1175
+ "pass@128": 0.668769716088328
1176
+ },
1177
+ "7": {
1178
+ "pass@1": 0.4272151898734177,
1179
+ "pass@2": 0.45569620253164556,
1180
+ "pass@4": 0.4778481012658228,
1181
+ "pass@8": 0.5063291139240507,
1182
+ "pass@16": 0.5158227848101266,
1183
+ "pass@32": 0.5348101265822784,
1184
+ "pass@64": 0.5537974683544303,
1185
+ "pass@128": 0.5727848101265823
1186
+ },
1187
+ "8": {
1188
+ "pass@1": 0.4174174174174174,
1189
+ "pass@2": 0.4594594594594595,
1190
+ "pass@4": 0.4804804804804805,
1191
+ "pass@8": 0.4924924924924925,
1192
+ "pass@16": 0.5135135135135135,
1193
+ "pass@32": 0.5375375375375375,
1194
+ "pass@64": 0.5525525525525525,
1195
+ "pass@128": 0.5765765765765766
1196
+ },
1197
+ "9": {
1198
+ "pass@1": 0.4405144694533762,
1199
+ "pass@2": 0.4919614147909968,
1200
+ "pass@4": 0.5080385852090032,
1201
+ "pass@8": 0.5241157556270096,
1202
+ "pass@16": 0.5434083601286174,
1203
+ "pass@32": 0.5562700964630225,
1204
+ "pass@64": 0.5627009646302251,
1205
+ "pass@128": 0.5755627009646302
1206
+ },
1207
+ "10": {
1208
+ "pass@1": 0.417910447761194,
1209
+ "pass@2": 0.4417910447761194,
1210
+ "pass@4": 0.46865671641791046,
1211
+ "pass@8": 0.47761194029850745,
1212
+ "pass@16": 0.48656716417910445,
1213
+ "pass@32": 0.5014925373134328,
1214
+ "pass@64": 0.5134328358208955,
1215
+ "pass@128": 0.5134328358208955
1216
+ }
1217
+ },
1218
+ "per_op_pass_at_columns": {
1219
+ "pass@1": {
1220
+ "2": 0.8857142857142857,
1221
+ "3": 0.880466472303207,
1222
+ "4": 0.6754385964912281,
1223
+ "5": 0.5294117647058824,
1224
+ "6": 0.48580441640378547,
1225
+ "7": 0.4272151898734177,
1226
+ "8": 0.4174174174174174,
1227
+ "9": 0.4405144694533762,
1228
+ "10": 0.417910447761194
1229
+ },
1230
+ "pass@2": {
1231
+ "2": 0.9171428571428571,
1232
+ "3": 0.9037900874635568,
1233
+ "4": 0.7134502923976608,
1234
+ "5": 0.5676470588235294,
1235
+ "6": 0.5236593059936908,
1236
+ "7": 0.45569620253164556,
1237
+ "8": 0.4594594594594595,
1238
+ "9": 0.4919614147909968,
1239
+ "10": 0.4417910447761194
1240
+ },
1241
+ "pass@4": {
1242
+ "2": 0.9314285714285714,
1243
+ "3": 0.9212827988338192,
1244
+ "4": 0.7339181286549707,
1245
+ "5": 0.611764705882353,
1246
+ "6": 0.5488958990536278,
1247
+ "7": 0.4778481012658228,
1248
+ "8": 0.4804804804804805,
1249
+ "9": 0.5080385852090032,
1250
+ "10": 0.46865671641791046
1251
+ },
1252
+ "pass@8": {
1253
+ "2": 0.9514285714285714,
1254
+ "3": 0.9358600583090378,
1255
+ "4": 0.7456140350877193,
1256
+ "5": 0.6294117647058823,
1257
+ "6": 0.580441640378549,
1258
+ "7": 0.5063291139240507,
1259
+ "8": 0.4924924924924925,
1260
+ "9": 0.5241157556270096,
1261
+ "10": 0.47761194029850745
1262
+ },
1263
+ "pass@16": {
1264
+ "2": 0.9657142857142857,
1265
+ "3": 0.9416909620991254,
1266
+ "4": 0.7602339181286549,
1267
+ "5": 0.6529411764705882,
1268
+ "6": 0.6056782334384858,
1269
+ "7": 0.5158227848101266,
1270
+ "8": 0.5135135135135135,
1271
+ "9": 0.5434083601286174,
1272
+ "10": 0.48656716417910445
1273
+ },
1274
+ "pass@32": {
1275
+ "2": 0.9685714285714285,
1276
+ "3": 0.9533527696793003,
1277
+ "4": 0.7748538011695907,
1278
+ "5": 0.6588235294117647,
1279
+ "6": 0.6214511041009464,
1280
+ "7": 0.5348101265822784,
1281
+ "8": 0.5375375375375375,
1282
+ "9": 0.5562700964630225,
1283
+ "10": 0.5014925373134328
1284
+ },
1285
+ "pass@64": {
1286
+ "2": 0.98,
1287
+ "3": 0.967930029154519,
1288
+ "4": 0.804093567251462,
1289
+ "5": 0.6735294117647059,
1290
+ "6": 0.6466876971608833,
1291
+ "7": 0.5537974683544303,
1292
+ "8": 0.5525525525525525,
1293
+ "9": 0.5627009646302251,
1294
+ "10": 0.5134328358208955
1295
+ },
1296
+ "pass@128": {
1297
+ "2": 0.9885714285714285,
1298
+ "3": 0.9708454810495627,
1299
+ "4": 0.8099415204678363,
1300
+ "5": 0.6911764705882353,
1301
+ "6": 0.668769716088328,
1302
+ "7": 0.5727848101265823,
1303
+ "8": 0.5765765765765766,
1304
+ "9": 0.5755627009646302,
1305
+ "10": 0.5134328358208955
1306
+ }
1307
+ },
1308
+ "total_pass_at_k": {
1309
+ "pass@1": 0.5785068630733177,
1310
+ "pass@2": 0.613324405758286,
1311
+ "pass@4": 0.6364245061935052,
1312
+ "pass@8": 0.6541680616002679,
1313
+ "pass@16": 0.6699029126213593,
1314
+ "pass@32": 0.6832942751925009,
1315
+ "pass@64": 0.6996986943421493,
1316
+ "pass@128": 0.7120857047204553
1317
+ }
1318
+ },
1319
+ "teachers_in_school": {
1320
+ "per_op_pass_at_k": {
1321
+ "2": {
1322
+ "pass@1": 0.9209726443768997,
1323
+ "pass@2": 0.9331306990881459,
1324
+ "pass@4": 0.9483282674772037,
1325
+ "pass@8": 0.9604863221884499,
1326
+ "pass@16": 0.9787234042553191,
1327
+ "pass@32": 0.9817629179331308,
1328
+ "pass@64": 0.9878419452887538,
1329
+ "pass@128": 0.9878419452887538
1330
+ },
1331
+ "3": {
1332
+ "pass@1": 0.8848484848484849,
1333
+ "pass@2": 0.906060606060606,
1334
+ "pass@4": 0.9212121212121213,
1335
+ "pass@8": 0.9424242424242424,
1336
+ "pass@16": 0.9484848484848485,
1337
+ "pass@32": 0.9606060606060606,
1338
+ "pass@64": 0.9696969696969697,
1339
+ "pass@128": 0.9696969696969697
1340
+ },
1341
+ "4": {
1342
+ "pass@1": 0.6390532544378699,
1343
+ "pass@2": 0.6775147928994083,
1344
+ "pass@4": 0.7011834319526628,
1345
+ "pass@8": 0.727810650887574,
1346
+ "pass@16": 0.7514792899408284,
1347
+ "pass@32": 0.7633136094674556,
1348
+ "pass@64": 0.7869822485207101,
1349
+ "pass@128": 0.7958579881656804
1350
+ },
1351
+ "5": {
1352
+ "pass@1": 0.5739130434782609,
1353
+ "pass@2": 0.6,
1354
+ "pass@4": 0.6202898550724638,
1355
+ "pass@8": 0.6347826086956522,
1356
+ "pass@16": 0.6666666666666666,
1357
+ "pass@32": 0.7014492753623188,
1358
+ "pass@64": 0.7188405797101449,
1359
+ "pass@128": 0.7304347826086957
1360
+ },
1361
+ "6": {
1362
+ "pass@1": 0.4699140401146132,
1363
+ "pass@2": 0.49570200573065903,
1364
+ "pass@4": 0.5214899713467048,
1365
+ "pass@8": 0.5530085959885387,
1366
+ "pass@16": 0.5816618911174785,
1367
+ "pass@32": 0.5988538681948424,
1368
+ "pass@64": 0.6246418338108882,
1369
+ "pass@128": 0.6361031518624641
1370
+ },
1371
+ "7": {
1372
+ "pass@1": 0.4653179190751445,
1373
+ "pass@2": 0.48265895953757226,
1374
+ "pass@4": 0.5086705202312138,
1375
+ "pass@8": 0.5375722543352601,
1376
+ "pass@16": 0.5491329479768786,
1377
+ "pass@32": 0.5664739884393064,
1378
+ "pass@64": 0.5780346820809249,
1379
+ "pass@128": 0.5924855491329479
1380
+ },
1381
+ "8": {
1382
+ "pass@1": 0.4253521126760563,
1383
+ "pass@2": 0.4535211267605634,
1384
+ "pass@4": 0.476056338028169,
1385
+ "pass@8": 0.48732394366197185,
1386
+ "pass@16": 0.5126760563380282,
1387
+ "pass@32": 0.5295774647887324,
1388
+ "pass@64": 0.5352112676056338,
1389
+ "pass@128": 0.5464788732394367
1390
+ },
1391
+ "9": {
1392
+ "pass@1": 0.39820359281437123,
1393
+ "pass@2": 0.4311377245508982,
1394
+ "pass@4": 0.44610778443113774,
1395
+ "pass@8": 0.46706586826347307,
1396
+ "pass@16": 0.4880239520958084,
1397
+ "pass@32": 0.49700598802395207,
1398
+ "pass@64": 0.5239520958083832,
1399
+ "pass@128": 0.5389221556886228
1400
+ },
1401
+ "10": {
1402
+ "pass@1": 0.49079754601226994,
1403
+ "pass@2": 0.49693251533742333,
1404
+ "pass@4": 0.50920245398773,
1405
+ "pass@8": 0.50920245398773,
1406
+ "pass@16": 0.5184049079754601,
1407
+ "pass@32": 0.5337423312883436,
1408
+ "pass@64": 0.5337423312883436,
1409
+ "pass@128": 0.5429447852760736
1410
+ }
1411
+ },
1412
+ "per_op_pass_at_columns": {
1413
+ "pass@1": {
1414
+ "2": 0.9209726443768997,
1415
+ "3": 0.8848484848484849,
1416
+ "4": 0.6390532544378699,
1417
+ "5": 0.5739130434782609,
1418
+ "6": 0.4699140401146132,
1419
+ "7": 0.4653179190751445,
1420
+ "8": 0.4253521126760563,
1421
+ "9": 0.39820359281437123,
1422
+ "10": 0.49079754601226994
1423
+ },
1424
+ "pass@2": {
1425
+ "2": 0.9331306990881459,
1426
+ "3": 0.906060606060606,
1427
+ "4": 0.6775147928994083,
1428
+ "5": 0.6,
1429
+ "6": 0.49570200573065903,
1430
+ "7": 0.48265895953757226,
1431
+ "8": 0.4535211267605634,
1432
+ "9": 0.4311377245508982,
1433
+ "10": 0.49693251533742333
1434
+ },
1435
+ "pass@4": {
1436
+ "2": 0.9483282674772037,
1437
+ "3": 0.9212121212121213,
1438
+ "4": 0.7011834319526628,
1439
+ "5": 0.6202898550724638,
1440
+ "6": 0.5214899713467048,
1441
+ "7": 0.5086705202312138,
1442
+ "8": 0.476056338028169,
1443
+ "9": 0.44610778443113774,
1444
+ "10": 0.50920245398773
1445
+ },
1446
+ "pass@8": {
1447
+ "2": 0.9604863221884499,
1448
+ "3": 0.9424242424242424,
1449
+ "4": 0.727810650887574,
1450
+ "5": 0.6347826086956522,
1451
+ "6": 0.5530085959885387,
1452
+ "7": 0.5375722543352601,
1453
+ "8": 0.48732394366197185,
1454
+ "9": 0.46706586826347307,
1455
+ "10": 0.50920245398773
1456
+ },
1457
+ "pass@16": {
1458
+ "2": 0.9787234042553191,
1459
+ "3": 0.9484848484848485,
1460
+ "4": 0.7514792899408284,
1461
+ "5": 0.6666666666666666,
1462
+ "6": 0.5816618911174785,
1463
+ "7": 0.5491329479768786,
1464
+ "8": 0.5126760563380282,
1465
+ "9": 0.4880239520958084,
1466
+ "10": 0.5184049079754601
1467
+ },
1468
+ "pass@32": {
1469
+ "2": 0.9817629179331308,
1470
+ "3": 0.9606060606060606,
1471
+ "4": 0.7633136094674556,
1472
+ "5": 0.7014492753623188,
1473
+ "6": 0.5988538681948424,
1474
+ "7": 0.5664739884393064,
1475
+ "8": 0.5295774647887324,
1476
+ "9": 0.49700598802395207,
1477
+ "10": 0.5337423312883436
1478
+ },
1479
+ "pass@64": {
1480
+ "2": 0.9878419452887538,
1481
+ "3": 0.9696969696969697,
1482
+ "4": 0.7869822485207101,
1483
+ "5": 0.7188405797101449,
1484
+ "6": 0.6246418338108882,
1485
+ "7": 0.5780346820809249,
1486
+ "8": 0.5352112676056338,
1487
+ "9": 0.5239520958083832,
1488
+ "10": 0.5337423312883436
1489
+ },
1490
+ "pass@128": {
1491
+ "2": 0.9878419452887538,
1492
+ "3": 0.9696969696969697,
1493
+ "4": 0.7958579881656804,
1494
+ "5": 0.7304347826086957,
1495
+ "6": 0.6361031518624641,
1496
+ "7": 0.5924855491329479,
1497
+ "8": 0.5464788732394367,
1498
+ "9": 0.5389221556886228,
1499
+ "10": 0.5429447852760736
1500
+ }
1501
+ },
1502
+ "total_pass_at_k": {
1503
+ "pass@1": 0.5825688073394495,
1504
+ "pass@2": 0.6058322411533421,
1505
+ "pass@4": 0.6254914809960681,
1506
+ "pass@8": 0.6441677588466579,
1507
+ "pass@16": 0.663826998689384,
1508
+ "pass@32": 0.6792267365661862,
1509
+ "pass@64": 0.6933158584534731,
1510
+ "pass@128": 0.7024901703800787
1511
+ }
1512
+ }
1513
+ },
1514
+ "total": {
1515
+ "per_op_pass_at_k": {
1516
+ "2": {
1517
+ "pass@1": 0.904,
1518
+ "pass@2": 0.933,
1519
+ "pass@4": 0.947,
1520
+ "pass@8": 0.959,
1521
+ "pass@16": 0.975,
1522
+ "pass@32": 0.978,
1523
+ "pass@64": 0.984,
1524
+ "pass@128": 0.988
1525
+ },
1526
+ "3": {
1527
+ "pass@1": 0.87,
1528
+ "pass@2": 0.896,
1529
+ "pass@4": 0.913,
1530
+ "pass@8": 0.932,
1531
+ "pass@16": 0.943,
1532
+ "pass@32": 0.955,
1533
+ "pass@64": 0.965,
1534
+ "pass@128": 0.969
1535
+ },
1536
+ "4": {
1537
+ "pass@1": 0.661,
1538
+ "pass@2": 0.694,
1539
+ "pass@4": 0.712,
1540
+ "pass@8": 0.728,
1541
+ "pass@16": 0.749,
1542
+ "pass@32": 0.76,
1543
+ "pass@64": 0.783,
1544
+ "pass@128": 0.794
1545
+ },
1546
+ "5": {
1547
+ "pass@1": 0.549,
1548
+ "pass@2": 0.583,
1549
+ "pass@4": 0.61,
1550
+ "pass@8": 0.632,
1551
+ "pass@16": 0.655,
1552
+ "pass@32": 0.673,
1553
+ "pass@64": 0.688,
1554
+ "pass@128": 0.706
1555
+ },
1556
+ "6": {
1557
+ "pass@1": 0.486,
1558
+ "pass@2": 0.52,
1559
+ "pass@4": 0.544,
1560
+ "pass@8": 0.571,
1561
+ "pass@16": 0.598,
1562
+ "pass@32": 0.616,
1563
+ "pass@64": 0.64,
1564
+ "pass@128": 0.662
1565
+ },
1566
+ "7": {
1567
+ "pass@1": 0.461,
1568
+ "pass@2": 0.483,
1569
+ "pass@4": 0.508,
1570
+ "pass@8": 0.535,
1571
+ "pass@16": 0.548,
1572
+ "pass@32": 0.566,
1573
+ "pass@64": 0.585,
1574
+ "pass@128": 0.6
1575
+ },
1576
+ "8": {
1577
+ "pass@1": 0.428,
1578
+ "pass@2": 0.462,
1579
+ "pass@4": 0.482,
1580
+ "pass@8": 0.497,
1581
+ "pass@16": 0.517,
1582
+ "pass@32": 0.533,
1583
+ "pass@64": 0.545,
1584
+ "pass@128": 0.561
1585
+ },
1586
+ "9": {
1587
+ "pass@1": 0.422,
1588
+ "pass@2": 0.464,
1589
+ "pass@4": 0.487,
1590
+ "pass@8": 0.506,
1591
+ "pass@16": 0.528,
1592
+ "pass@32": 0.542,
1593
+ "pass@64": 0.56,
1594
+ "pass@128": 0.571
1595
+ },
1596
+ "10": {
1597
+ "pass@1": 0.462,
1598
+ "pass@2": 0.474,
1599
+ "pass@4": 0.493,
1600
+ "pass@8": 0.499,
1601
+ "pass@16": 0.508,
1602
+ "pass@32": 0.519,
1603
+ "pass@64": 0.527,
1604
+ "pass@128": 0.532
1605
+ }
1606
+ },
1607
+ "per_op_pass_at_columns": {
1608
+ "pass@1": {
1609
+ "2": 0.904,
1610
+ "3": 0.87,
1611
+ "4": 0.661,
1612
+ "5": 0.549,
1613
+ "6": 0.486,
1614
+ "7": 0.461,
1615
+ "8": 0.428,
1616
+ "9": 0.422,
1617
+ "10": 0.462
1618
+ },
1619
+ "pass@2": {
1620
+ "2": 0.933,
1621
+ "3": 0.896,
1622
+ "4": 0.694,
1623
+ "5": 0.583,
1624
+ "6": 0.52,
1625
+ "7": 0.483,
1626
+ "8": 0.462,
1627
+ "9": 0.464,
1628
+ "10": 0.474
1629
+ },
1630
+ "pass@4": {
1631
+ "2": 0.947,
1632
+ "3": 0.913,
1633
+ "4": 0.712,
1634
+ "5": 0.61,
1635
+ "6": 0.544,
1636
+ "7": 0.508,
1637
+ "8": 0.482,
1638
+ "9": 0.487,
1639
+ "10": 0.493
1640
+ },
1641
+ "pass@8": {
1642
+ "2": 0.959,
1643
+ "3": 0.932,
1644
+ "4": 0.728,
1645
+ "5": 0.632,
1646
+ "6": 0.571,
1647
+ "7": 0.535,
1648
+ "8": 0.497,
1649
+ "9": 0.506,
1650
+ "10": 0.499
1651
+ },
1652
+ "pass@16": {
1653
+ "2": 0.975,
1654
+ "3": 0.943,
1655
+ "4": 0.749,
1656
+ "5": 0.655,
1657
+ "6": 0.598,
1658
+ "7": 0.548,
1659
+ "8": 0.517,
1660
+ "9": 0.528,
1661
+ "10": 0.508
1662
+ },
1663
+ "pass@32": {
1664
+ "2": 0.978,
1665
+ "3": 0.955,
1666
+ "4": 0.76,
1667
+ "5": 0.673,
1668
+ "6": 0.616,
1669
+ "7": 0.566,
1670
+ "8": 0.533,
1671
+ "9": 0.542,
1672
+ "10": 0.519
1673
+ },
1674
+ "pass@64": {
1675
+ "2": 0.984,
1676
+ "3": 0.965,
1677
+ "4": 0.783,
1678
+ "5": 0.688,
1679
+ "6": 0.64,
1680
+ "7": 0.585,
1681
+ "8": 0.545,
1682
+ "9": 0.56,
1683
+ "10": 0.527
1684
+ },
1685
+ "pass@128": {
1686
+ "2": 0.988,
1687
+ "3": 0.969,
1688
+ "4": 0.794,
1689
+ "5": 0.706,
1690
+ "6": 0.662,
1691
+ "7": 0.6,
1692
+ "8": 0.561,
1693
+ "9": 0.571,
1694
+ "10": 0.532
1695
+ }
1696
+ },
1697
+ "total_pass_at_k": {
1698
+ "pass@1": 0.5825555555555556,
1699
+ "pass@2": 0.6121111111111112,
1700
+ "pass@4": 0.6328888888888888,
1701
+ "pass@8": 0.651,
1702
+ "pass@16": 0.669,
1703
+ "pass@32": 0.6824444444444444,
1704
+ "pass@64": 0.6974444444444444,
1705
+ "pass@128": 0.7092222222222222
1706
+ }
1707
+ },
1708
+ "ks": [
1709
+ 1,
1710
+ 2,
1711
+ 4,
1712
+ 8,
1713
+ 16,
1714
+ 32,
1715
+ 64,
1716
+ 128
1717
+ ],
1718
+ "prompt_counts": {
1719
+ "per_template": {
1720
+ "crazy_zootopia": {
1721
+ "per_op": {
1722
+ "2": 321,
1723
+ "3": 327,
1724
+ "4": 320,
1725
+ "5": 315,
1726
+ "6": 334,
1727
+ "7": 338,
1728
+ "8": 312,
1729
+ "9": 355,
1730
+ "10": 339
1731
+ },
1732
+ "total": 2961
1733
+ },
1734
+ "movie_festival_awards": {
1735
+ "per_op": {
1736
+ "2": 350,
1737
+ "3": 343,
1738
+ "4": 342,
1739
+ "5": 340,
1740
+ "6": 317,
1741
+ "7": 316,
1742
+ "8": 333,
1743
+ "9": 311,
1744
+ "10": 335
1745
+ },
1746
+ "total": 2987
1747
+ },
1748
+ "teachers_in_school": {
1749
+ "per_op": {
1750
+ "2": 329,
1751
+ "3": 330,
1752
+ "4": 338,
1753
+ "5": 345,
1754
+ "6": 349,
1755
+ "7": 346,
1756
+ "8": 355,
1757
+ "9": 334,
1758
+ "10": 326
1759
+ },
1760
+ "total": 3052
1761
+ }
1762
+ },
1763
+ "total": {
1764
+ "per_op": {
1765
+ "2": 1000,
1766
+ "3": 1000,
1767
+ "4": 1000,
1768
+ "5": 1000,
1769
+ "6": 1000,
1770
+ "7": 1000,
1771
+ "8": 1000,
1772
+ "9": 1000,
1773
+ "10": 1000
1774
+ },
1775
+ "total": 9000
1776
+ }
1777
+ }
1778
+ }
1779
+ }
1780
+ }