narcolepticchicken commited on
Commit
391292b
·
verified ·
1 Parent(s): 1352f0b

Upload router_models/v6_eval_results.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. router_models/v6_eval_results.json +304 -0
router_models/v6_eval_results.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "always_frontier": {
3
+ "success": 0.8935,
4
+ "avg_cost": 1.0,
5
+ "unsafe_rate": 0.023,
6
+ "false_done": 0.0835,
7
+ "tier_dist": {
8
+ "4": 2000
9
+ },
10
+ "escalations": 878,
11
+ "downgrades": 420,
12
+ "heuristic_only": 702
13
+ },
14
+ "always_cheap": {
15
+ "success": 0.2225,
16
+ "avg_cost": 0.04999999999999823,
17
+ "unsafe_rate": 0.7775,
18
+ "false_done": 0.0,
19
+ "tier_dist": {
20
+ "1": 2000
21
+ },
22
+ "escalations": 0,
23
+ "downgrades": 2000,
24
+ "heuristic_only": 0
25
+ },
26
+ "heuristic_diff+1": {
27
+ "success": 0.8405,
28
+ "avg_cost": 0.9271500000000037,
29
+ "unsafe_rate": 0.047,
30
+ "false_done": 0.1125,
31
+ "tier_dist": {
32
+ "4": 702,
33
+ "3": 651,
34
+ "5": 420,
35
+ "2": 227
36
+ },
37
+ "escalations": 0,
38
+ "downgrades": 0,
39
+ "heuristic_only": 2000
40
+ },
41
+ "heuristic_floor": {
42
+ "success": 0.5875,
43
+ "avg_cost": 0.5013749999999922,
44
+ "unsafe_rate": 0.28,
45
+ "false_done": 0.1325,
46
+ "tier_dist": {
47
+ "3": 913,
48
+ "2": 651,
49
+ "4": 209,
50
+ "1": 227
51
+ },
52
+ "escalations": 0,
53
+ "downgrades": 2000,
54
+ "heuristic_only": 0
55
+ },
56
+ "oracle": {
57
+ "success": 0.998,
58
+ "avg_cost": 0.47694999999999094,
59
+ "unsafe_rate": 0.0,
60
+ "false_done": 0.002,
61
+ "tier_dist": {
62
+ "3": 644,
63
+ "5": 46,
64
+ "2": 571,
65
+ "4": 294,
66
+ "1": 445
67
+ },
68
+ "escalations": 94,
69
+ "downgrades": 1486,
70
+ "heuristic_only": 420
71
+ },
72
+ "hybrid_s0.25_d0.70": {
73
+ "success": 0.8175,
74
+ "avg_cost": 0.8221500000000023,
75
+ "unsafe_rate": 0.0595,
76
+ "false_done": 0.123,
77
+ "tier_dist": {
78
+ "4": 1122,
79
+ "3": 651,
80
+ "2": 227
81
+ },
82
+ "escalations": 0,
83
+ "downgrades": 420,
84
+ "heuristic_only": 1580
85
+ },
86
+ "hybrid_s0.25_d0.75": {
87
+ "success": 0.8175,
88
+ "avg_cost": 0.8221500000000023,
89
+ "unsafe_rate": 0.0595,
90
+ "false_done": 0.123,
91
+ "tier_dist": {
92
+ "4": 1122,
93
+ "3": 651,
94
+ "2": 227
95
+ },
96
+ "escalations": 0,
97
+ "downgrades": 420,
98
+ "heuristic_only": 1580
99
+ },
100
+ "hybrid_s0.25_d0.80": {
101
+ "success": 0.8225,
102
+ "avg_cost": 0.8416500000000027,
103
+ "unsafe_rate": 0.058,
104
+ "false_done": 0.1195,
105
+ "tier_dist": {
106
+ "4": 1044,
107
+ "3": 651,
108
+ "5": 78,
109
+ "2": 227
110
+ },
111
+ "escalations": 0,
112
+ "downgrades": 342,
113
+ "heuristic_only": 1658
114
+ },
115
+ "hybrid_s0.25_d0.85": {
116
+ "success": 0.838,
117
+ "avg_cost": 0.9084000000000035,
118
+ "unsafe_rate": 0.048,
119
+ "false_done": 0.114,
120
+ "tier_dist": {
121
+ "4": 777,
122
+ "3": 651,
123
+ "5": 345,
124
+ "2": 227
125
+ },
126
+ "escalations": 0,
127
+ "downgrades": 75,
128
+ "heuristic_only": 1925
129
+ },
130
+ "hybrid_s0.30_d0.70": {
131
+ "success": 0.8175,
132
+ "avg_cost": 0.8221500000000023,
133
+ "unsafe_rate": 0.0595,
134
+ "false_done": 0.123,
135
+ "tier_dist": {
136
+ "4": 1122,
137
+ "3": 651,
138
+ "2": 227
139
+ },
140
+ "escalations": 0,
141
+ "downgrades": 420,
142
+ "heuristic_only": 1580
143
+ },
144
+ "hybrid_s0.30_d0.75": {
145
+ "success": 0.8175,
146
+ "avg_cost": 0.8221500000000023,
147
+ "unsafe_rate": 0.0595,
148
+ "false_done": 0.123,
149
+ "tier_dist": {
150
+ "4": 1122,
151
+ "3": 651,
152
+ "2": 227
153
+ },
154
+ "escalations": 0,
155
+ "downgrades": 420,
156
+ "heuristic_only": 1580
157
+ },
158
+ "hybrid_s0.30_d0.80": {
159
+ "success": 0.8225,
160
+ "avg_cost": 0.8416500000000027,
161
+ "unsafe_rate": 0.058,
162
+ "false_done": 0.1195,
163
+ "tier_dist": {
164
+ "4": 1044,
165
+ "3": 651,
166
+ "5": 78,
167
+ "2": 227
168
+ },
169
+ "escalations": 0,
170
+ "downgrades": 342,
171
+ "heuristic_only": 1658
172
+ },
173
+ "hybrid_s0.30_d0.85": {
174
+ "success": 0.838,
175
+ "avg_cost": 0.9084000000000035,
176
+ "unsafe_rate": 0.048,
177
+ "false_done": 0.114,
178
+ "tier_dist": {
179
+ "4": 777,
180
+ "3": 651,
181
+ "5": 345,
182
+ "2": 227
183
+ },
184
+ "escalations": 0,
185
+ "downgrades": 75,
186
+ "heuristic_only": 1925
187
+ },
188
+ "hybrid_s0.35_d0.70": {
189
+ "success": 0.8175,
190
+ "avg_cost": 0.8221500000000023,
191
+ "unsafe_rate": 0.0595,
192
+ "false_done": 0.123,
193
+ "tier_dist": {
194
+ "4": 1122,
195
+ "3": 651,
196
+ "2": 227
197
+ },
198
+ "escalations": 0,
199
+ "downgrades": 420,
200
+ "heuristic_only": 1580
201
+ },
202
+ "hybrid_s0.35_d0.75": {
203
+ "success": 0.8175,
204
+ "avg_cost": 0.8221500000000023,
205
+ "unsafe_rate": 0.0595,
206
+ "false_done": 0.123,
207
+ "tier_dist": {
208
+ "4": 1122,
209
+ "3": 651,
210
+ "2": 227
211
+ },
212
+ "escalations": 0,
213
+ "downgrades": 420,
214
+ "heuristic_only": 1580
215
+ },
216
+ "hybrid_s0.35_d0.80": {
217
+ "success": 0.8225,
218
+ "avg_cost": 0.8416500000000027,
219
+ "unsafe_rate": 0.058,
220
+ "false_done": 0.1195,
221
+ "tier_dist": {
222
+ "4": 1044,
223
+ "3": 651,
224
+ "5": 78,
225
+ "2": 227
226
+ },
227
+ "escalations": 0,
228
+ "downgrades": 342,
229
+ "heuristic_only": 1658
230
+ },
231
+ "hybrid_s0.35_d0.85": {
232
+ "success": 0.838,
233
+ "avg_cost": 0.9084000000000035,
234
+ "unsafe_rate": 0.048,
235
+ "false_done": 0.114,
236
+ "tier_dist": {
237
+ "4": 777,
238
+ "3": 651,
239
+ "5": 345,
240
+ "2": 227
241
+ },
242
+ "escalations": 0,
243
+ "downgrades": 75,
244
+ "heuristic_only": 1925
245
+ },
246
+ "hybrid_s0.40_d0.70": {
247
+ "success": 0.8175,
248
+ "avg_cost": 0.8221500000000023,
249
+ "unsafe_rate": 0.0595,
250
+ "false_done": 0.123,
251
+ "tier_dist": {
252
+ "4": 1122,
253
+ "3": 651,
254
+ "2": 227
255
+ },
256
+ "escalations": 0,
257
+ "downgrades": 420,
258
+ "heuristic_only": 1580
259
+ },
260
+ "hybrid_s0.40_d0.75": {
261
+ "success": 0.8175,
262
+ "avg_cost": 0.8221500000000023,
263
+ "unsafe_rate": 0.0595,
264
+ "false_done": 0.123,
265
+ "tier_dist": {
266
+ "4": 1122,
267
+ "3": 651,
268
+ "2": 227
269
+ },
270
+ "escalations": 0,
271
+ "downgrades": 420,
272
+ "heuristic_only": 1580
273
+ },
274
+ "hybrid_s0.40_d0.80": {
275
+ "success": 0.8225,
276
+ "avg_cost": 0.8416500000000027,
277
+ "unsafe_rate": 0.058,
278
+ "false_done": 0.1195,
279
+ "tier_dist": {
280
+ "4": 1044,
281
+ "3": 651,
282
+ "5": 78,
283
+ "2": 227
284
+ },
285
+ "escalations": 0,
286
+ "downgrades": 342,
287
+ "heuristic_only": 1658
288
+ },
289
+ "hybrid_s0.40_d0.85": {
290
+ "success": 0.838,
291
+ "avg_cost": 0.9084000000000035,
292
+ "unsafe_rate": 0.048,
293
+ "false_done": 0.114,
294
+ "tier_dist": {
295
+ "4": 777,
296
+ "3": 651,
297
+ "5": 345,
298
+ "2": 227
299
+ },
300
+ "escalations": 0,
301
+ "downgrades": 75,
302
+ "heuristic_only": 1925
303
+ }
304
+ }