Views
No views yet
Write a 10-line poem about a given topic
Input:
The topic is about racecars
Output:Who was the was the second president of the United States?
Output:1{
2 "all": {
3 "acc": 0.6241143484289186,
4 "acc_stderr": 0.032689663124831826,
5 "acc_norm": 0.6299031400315822,
6 "acc_norm_stderr": 0.033361474961048916,
7 "mc1": 0.2802937576499388,
8 "mc1_stderr": 0.015723139524608767,
9 "mc2": 0.435601924823795,
10 "mc2_stderr": 0.014179199089974604
11 },
12 "harness|arc:challenge|25": {
13 "acc": 0.5571672354948806,
14 "acc_stderr": 0.014515573873348906,
15 "acc_norm": 0.5938566552901023,
16 "acc_norm_stderr": 0.014351656690097862
17 },
18 "harness|hellaswag|10": {
19 "acc": 0.6253734315873332,
20 "acc_stderr": 0.004830371317841054,
21 "acc_norm": 0.826229834694284,
22 "acc_norm_stderr": 0.00378137335887
23 },
24 "harness|hendrycksTest-abstract_algebra|5": {
25 "acc": 0.31,
26 "acc_stderr": 0.04648231987117316,
27 "acc_norm": 0.31,
28 "acc_norm_stderr": 0.04648231987117316
29 },
30 "harness|hendrycksTest-anatomy|5": {
31 "acc": 0.6148148148148148,
32 "acc_stderr": 0.04203921040156279,
33 "acc_norm": 0.6148148148148148,
34 "acc_norm_stderr": 0.04203921040156279
35 },
36 "harness|hendrycksTest-astronomy|5": {
37 "acc": 0.6513157894736842,
38 "acc_stderr": 0.03878139888797611,
39 "acc_norm": 0.6513157894736842,
40 "acc_norm_stderr": 0.03878139888797611
41 },
42 "harness|hendrycksTest-business_ethics|5": {
43 "acc": 0.57,
44 "acc_stderr": 0.04975698519562428,
45 "acc_norm": 0.57,
46 "acc_norm_stderr": 0.04975698519562428
47 },
48 "harness|hendrycksTest-clinical_knowledge|5": {
49 "acc": 0.660377358490566,
50 "acc_stderr": 0.029146904747798328,
51 "acc_norm": 0.660377358490566,
52 "acc_norm_stderr": 0.029146904747798328
53 },
54 "harness|hendrycksTest-college_biology|5": {
55 "acc": 0.7291666666666666,
56 "acc_stderr": 0.03716177437566017,
57 "acc_norm": 0.7291666666666666,
58 "acc_norm_stderr": 0.03716177437566017
59 },
60 "harness|hendrycksTest-college_chemistry|5": {
61 "acc": 0.46,
62 "acc_stderr": 0.05009082659620332,
63 "acc_norm": 0.46,
64 "acc_norm_stderr": 0.05009082659620332
65 },
66 "harness|hendrycksTest-college_computer_science|5": {
67 "acc": 0.54,
68 "acc_stderr": 0.05009082659620333,
69 "acc_norm": 0.54,
70 "acc_norm_stderr": 0.05009082659620333
71 },
72 "harness|hendrycksTest-college_mathematics|5": {
73 "acc": 0.38,
74 "acc_stderr": 0.04878317312145632,
75 "acc_norm": 0.38,
76 "acc_norm_stderr": 0.04878317312145632
77 },
78 "harness|hendrycksTest-college_medicine|5": {
79 "acc": 0.5838150289017341,
80 "acc_stderr": 0.03758517775404947,
81 "acc_norm": 0.5838150289017341,
82 "acc_norm_stderr": 0.03758517775404947
83 },
84 "harness|hendrycksTest-college_physics|5": {
85 "acc": 0.35294117647058826,
86 "acc_stderr": 0.04755129616062946,
87 "acc_norm": 0.35294117647058826,
88 "acc_norm_stderr": 0.04755129616062946
89 },
90 "harness|hendrycksTest-computer_security|5": {
91 "acc": 0.77,
92 "acc_stderr": 0.04229525846816505,
93 "acc_norm": 0.77,
94 "acc_norm_stderr": 0.04229525846816505
95 },
96 "harness|hendrycksTest-conceptual_physics|5": {
97 "acc": 0.5574468085106383,
98 "acc_stderr": 0.032469569197899575,
99 "acc_norm": 0.5574468085106383,
100 "acc_norm_stderr": 0.032469569197899575
101 },
102 "harness|hendrycksTest-econometrics|5": {
103 "acc": 0.5,
104 "acc_stderr": 0.047036043419179864,
105 "acc_norm": 0.5,
106 "acc_norm_stderr": 0.047036043419179864
107 },
108 "harness|hendrycksTest-electrical_engineering|5": {
109 "acc": 0.5724137931034483,
110 "acc_stderr": 0.041227371113703316,
111 "acc_norm": 0.5724137931034483,
112 "acc_norm_stderr": 0.041227371113703316
113 },
114 "harness|hendrycksTest-elementary_mathematics|5": {
115 "acc": 0.3994708994708995,
116 "acc_stderr": 0.02522545028406788,
117 "acc_norm": 0.3994708994708995,
118 "acc_norm_stderr": 0.02522545028406788
119 },
120 "harness|hendrycksTest-formal_logic|5": {
121 "acc": 0.3968253968253968,
122 "acc_stderr": 0.04375888492727061,
123 "acc_norm": 0.3968253968253968,
124 "acc_norm_stderr": 0.04375888492727061
125 },
126 "harness|hendrycksTest-global_facts|5": {
127 "acc": 0.35,
128 "acc_stderr": 0.0479372485441102,
129 "acc_norm": 0.35,
130 "acc_norm_stderr": 0.0479372485441102
131 },
132 "harness|hendrycksTest-high_school_biology|5": {
133 "acc": 0.7483870967741936,
134 "acc_stderr": 0.024685979286239956,
135 "acc_norm": 0.7483870967741936,
136 "acc_norm_stderr": 0.024685979286239956
137 },
138 "harness|hendrycksTest-high_school_chemistry|5": {
139 "acc": 0.5221674876847291,
140 "acc_stderr": 0.03514528562175008,
141 "acc_norm": 0.5221674876847291,
142 "acc_norm_stderr": 0.03514528562175008
143 },
144 "harness|hendrycksTest-high_school_computer_science|5": {
145 "acc": 0.67,
146 "acc_stderr": 0.04725815626252607,
147 "acc_norm": 0.67,
148 "acc_norm_stderr": 0.04725815626252607
149 },
150 "harness|hendrycksTest-high_school_european_history|5": {
151 "acc": 0.7636363636363637,
152 "acc_stderr": 0.03317505930009182,
153 "acc_norm": 0.7636363636363637,
154 "acc_norm_stderr": 0.03317505930009182
155 },
156 "harness|hendrycksTest-high_school_geography|5": {
157 "acc": 0.7525252525252525,
158 "acc_stderr": 0.030746300742124498,
159 "acc_norm": 0.7525252525252525,
160 "acc_norm_stderr": 0.030746300742124498
161 },
162 "harness|hendrycksTest-high_school_government_and_politics|5": {
163 "acc": 0.844559585492228,
164 "acc_stderr": 0.026148483469153314,
165 "acc_norm": 0.844559585492228,
166 "acc_norm_stderr": 0.026148483469153314
167 },
168 "harness|hendrycksTest-high_school_macroeconomics|5": {
169 "acc": 0.6205128205128205,
170 "acc_stderr": 0.024603626924097417,
171 "acc_norm": 0.6205128205128205,
172 "acc_norm_stderr": 0.024603626924097417
173 },
174 "harness|hendrycksTest-high_school_mathematics|5": {
175 "acc": 0.337037037037037,
176 "acc_stderr": 0.028820884666253252,
177 "acc_norm": 0.337037037037037,
178 "acc_norm_stderr": 0.028820884666253252
179 },
180 "harness|hendrycksTest-high_school_microeconomics|5": {
181 "acc": 0.6260504201680672,
182 "acc_stderr": 0.031429466378837076,
183 "acc_norm": 0.6260504201680672,
184 "acc_norm_stderr": 0.031429466378837076
185 },
186 "harness|hendrycksTest-high_school_physics|5": {
187 "acc": 0.33774834437086093,
188 "acc_stderr": 0.03861557546255169,
189 "acc_norm": 0.33774834437086093,
190 "acc_norm_stderr": 0.03861557546255169
191 },
192 "harness|hendrycksTest-high_school_psychology|5": {
193 "acc": 0.7944954128440367,
194 "acc_stderr": 0.01732435232501601,
195 "acc_norm": 0.7944954128440367,
196 "acc_norm_stderr": 0.01732435232501601
197 },
198 "harness|hendrycksTest-high_school_statistics|5": {
199 "acc": 0.5046296296296297,
200 "acc_stderr": 0.03409825519163572,
201 "acc_norm": 0.5046296296296297,
202 "acc_norm_stderr": 0.03409825519163572
203 },
204 "harness|hendrycksTest-high_school_us_history|5": {
205 "acc": 0.8137254901960784,
206 "acc_stderr": 0.027325470966716312,
207 "acc_norm": 0.8137254901960784,
208 "acc_norm_stderr": 0.027325470966716312
209 },
210 "harness|hendrycksTest-high_school_world_history|5": {
211 "acc": 0.7763713080168776,
212 "acc_stderr": 0.027123298205229966,
213 "acc_norm": 0.7763713080168776,
214 "acc_norm_stderr": 0.027123298205229966
215 },
216 "harness|hendrycksTest-human_aging|5": {
217 "acc": 0.6860986547085202,
218 "acc_stderr": 0.031146796482972465,
219 "acc_norm": 0.6860986547085202,
220 "acc_norm_stderr": 0.031146796482972465
221 },
222 "harness|hendrycksTest-human_sexuality|5": {
223 "acc": 0.7557251908396947,
224 "acc_stderr": 0.037683359597287434,
225 "acc_norm": 0.7557251908396947,
226 "acc_norm_stderr": 0.037683359597287434
227 },
228 "harness|hendrycksTest-international_law|5": {
229 "acc": 0.7851239669421488,
230 "acc_stderr": 0.037494924487096966,
231 "acc_norm": 0.7851239669421488,
232 "acc_norm_stderr": 0.037494924487096966
233 },
234 "harness|hendrycksTest-jurisprudence|5": {
235 "acc": 0.75,
236 "acc_stderr": 0.04186091791394607,
237 "acc_norm": 0.75,
238 "acc_norm_stderr": 0.04186091791394607
239 },
240 "harness|hendrycksTest-logical_fallacies|5": {
241 "acc": 0.7791411042944786,
242 "acc_stderr": 0.03259177392742178,
243 "acc_norm": 0.7791411042944786,
244 "acc_norm_stderr": 0.03259177392742178
245 },
246 "harness|hendrycksTest-machine_learning|5": {
247 "acc": 0.41964285714285715,
248 "acc_stderr": 0.04684099321077106,
249 "acc_norm": 0.41964285714285715,
250 "acc_norm_stderr": 0.04684099321077106
251 },
252 "harness|hendrycksTest-management|5": {
253 "acc": 0.7961165048543689,
254 "acc_stderr": 0.039891398595317706,
255 "acc_norm": 0.7961165048543689,
256 "acc_norm_stderr": 0.039891398595317706
257 },
258 "harness|hendrycksTest-marketing|5": {
259 "acc": 0.8589743589743589,
260 "acc_stderr": 0.022801382534597528,
261 "acc_norm": 0.8589743589743589,
262 "acc_norm_stderr": 0.022801382534597528
263 },
264 "harness|hendrycksTest-medical_genetics|5": {
265 "acc": 0.73,
266 "acc_stderr": 0.044619604333847394,
267 "acc_norm": 0.73,
268 "acc_norm_stderr": 0.044619604333847394
269 },
270 "harness|hendrycksTest-miscellaneous|5": {
271 "acc": 0.8135376756066411,
272 "acc_stderr": 0.013927751372001501,
273 "acc_norm": 0.8135376756066411,
274 "acc_norm_stderr": 0.013927751372001501
275 },
276 "harness|hendrycksTest-moral_disputes|5": {
277 "acc": 0.6994219653179191,
278 "acc_stderr": 0.0246853168672578,
279 "acc_norm": 0.6994219653179191,
280 "acc_norm_stderr": 0.0246853168672578
281 },
282 "harness|hendrycksTest-moral_scenarios|5": {
283 "acc": 0.4033519553072626,
284 "acc_stderr": 0.01640712303219525,
285 "acc_norm": 0.4033519553072626,
286 "acc_norm_stderr": 0.01640712303219525
287 },
288 "harness|hendrycksTest-nutrition|5": {
289 "acc": 0.7320261437908496,
290 "acc_stderr": 0.02536060379624255,
291 "acc_norm": 0.7320261437908496,
292 "acc_norm_stderr": 0.02536060379624255
293 },
294 "harness|hendrycksTest-philosophy|5": {
295 "acc": 0.7009646302250804,
296 "acc_stderr": 0.02600330111788514,
297 "acc_norm": 0.7009646302250804,
298 "acc_norm_stderr": 0.02600330111788514
299 },
300 "harness|hendrycksTest-prehistory|5": {
301 "acc": 0.7067901234567902,
302 "acc_stderr": 0.025329888171900926,
303 "acc_norm": 0.7067901234567902,
304 "acc_norm_stderr": 0.025329888171900926
305 },
306 "harness|hendrycksTest-professional_accounting|5": {
307 "acc": 0.49645390070921985,
308 "acc_stderr": 0.02982674915328092,
309 "acc_norm": 0.49645390070921985,
310 "acc_norm_stderr": 0.02982674915328092
311 },
312 "harness|hendrycksTest-professional_law|5": {
313 "acc": 0.44784876140808344,
314 "acc_stderr": 0.01270058240476822,
315 "acc_norm": 0.44784876140808344,
316 "acc_norm_stderr": 0.01270058240476822
317 },
318 "harness|hendrycksTest-professional_medicine|5": {
319 "acc": 0.6397058823529411,
320 "acc_stderr": 0.029163128570670733,
321 "acc_norm": 0.6397058823529411,
322 "acc_norm_stderr": 0.029163128570670733
323 },
324 "harness|hendrycksTest-professional_psychology|5": {
325 "acc": 0.6666666666666666,
326 "acc_stderr": 0.019070985589687495,
327 "acc_norm": 0.6666666666666666,
328 "acc_norm_stderr": 0.019070985589687495
329 },
330 "harness|hendrycksTest-public_relations|5": {
331 "acc": 0.6727272727272727,
332 "acc_stderr": 0.0449429086625209,
333 "acc_norm": 0.6727272727272727,
334 "acc_norm_stderr": 0.0449429086625209
335 },
336 "harness|hendrycksTest-security_studies|5": {
337 "acc": 0.7020408163265306,
338 "acc_stderr": 0.029279567411065677,
339 "acc_norm": 0.7020408163265306,
340 "acc_norm_stderr": 0.029279567411065677
341 },
342 "harness|hendrycksTest-sociology|5": {
343 "acc": 0.7960199004975125,
344 "acc_stderr": 0.02849317624532607,
345 "acc_norm": 0.7960199004975125,
346 "acc_norm_stderr": 0.02849317624532607
347 },
348 "harness|hendrycksTest-us_foreign_policy|5": {
349 "acc": 0.84,
350 "acc_stderr": 0.03684529491774709,
351 "acc_norm": 0.84,
352 "acc_norm_stderr": 0.03684529491774709
353 },
354 "harness|hendrycksTest-virology|5": {
355 "acc": 0.5542168674698795,
356 "acc_stderr": 0.03869543323472101,
357 "acc_norm": 0.5542168674698795,
358 "acc_norm_stderr": 0.03869543323472101
359 },
360 "harness|hendrycksTest-world_religions|5": {
361 "acc": 0.8011695906432749,
362 "acc_stderr": 0.03061111655743253,
363 "acc_norm": 0.8011695906432749,
364 "acc_norm_stderr": 0.03061111655743253
365 },
366 "harness|truthfulqa:mc|0": {
367 "mc1": 0.2802937576499388,
368 "mc1_stderr": 0.015723139524608767,
369 "mc2": 0.435601924823795,
370 "mc2_stderr": 0.014179199089974604
371 },
372 "harness|winogrande|5": {
373 "acc": 0.7932123125493291,
374 "acc_stderr": 0.011382566829235805
375 },
376 "harness|gsm8k|5": {
377 "acc": 0.3510235026535254,
378 "acc_stderr": 0.01314694594139722
379 }
380}