multiple_choice_score: there are 789 tasks in prompt | |
multiple_choice_score: reading tasks................................................................................................................done | |
multiple_choice_score: preparing task data...done | |
multiple_choice_score : calculating TruthfulQA score over 789 tasks. | |
task acc_norm | |
1 100.00000000 | |
2 50.00000000 | |
3 33.33333333 | |
4 25.00000000 | |
5 40.00000000 | |
6 33.33333333 | |
7 28.57142857 | |
8 25.00000000 | |
9 22.22222222 | |
10 20.00000000 | |
11 18.18181818 | |
12 16.66666667 | |
13 23.07692308 | |
14 21.42857143 | |
15 20.00000000 | |
16 18.75000000 | |
17 17.64705882 | |
18 22.22222222 | |
19 21.05263158 | |
20 20.00000000 | |
21 19.04761905 | |
22 18.18181818 | |
23 17.39130435 | |
24 16.66666667 | |
25 16.00000000 | |
26 19.23076923 | |
27 18.51851852 | |
28 21.42857143 | |
29 20.68965517 | |
30 23.33333333 | |
31 25.80645161 | |
32 25.00000000 | |
33 24.24242424 | |
34 26.47058824 | |
35 25.71428571 | |
36 25.00000000 | |
37 24.32432432 | |
38 26.31578947 | |
39 28.20512821 | |
40 27.50000000 | |
41 26.82926829 | |
42 26.19047619 | |
43 25.58139535 | |
44 25.00000000 | |
45 24.44444444 | |
46 23.91304348 | |
47 23.40425532 | |
48 25.00000000 | |
49 24.48979592 | |
50 24.00000000 | |
51 23.52941176 | |
52 23.07692308 | |
53 24.52830189 | |
54 24.07407407 | |
55 23.63636364 | |
56 23.21428571 | |
57 24.56140351 | |
58 25.86206897 | |
59 25.42372881 | |
60 25.00000000 | |
61 24.59016393 | |
62 24.19354839 | |
63 23.80952381 | |
64 23.43750000 | |
65 23.07692308 | |
66 22.72727273 | |
67 22.38805970 | |
68 22.05882353 | |
69 21.73913043 | |
70 21.42857143 | |
71 21.12676056 | |
72 20.83333333 | |
73 20.54794521 | |
74 21.62162162 | |
75 22.66666667 | |
76 23.68421053 | |
77 23.37662338 | |
78 23.07692308 | |
79 22.78481013 | |
80 23.75000000 | |
81 23.45679012 | |
82 23.17073171 | |
83 22.89156627 | |
84 22.61904762 | |
85 22.35294118 | |
86 22.09302326 | |
87 21.83908046 | |
88 21.59090909 | |
89 21.34831461 | |
90 21.11111111 | |
91 20.87912088 | |
92 20.65217391 | |
93 20.43010753 | |
94 20.21276596 | |
95 20.00000000 | |
96 19.79166667 | |
97 19.58762887 | |
98 19.38775510 | |
99 19.19191919 | |
100 19.00000000 | |
101 18.81188119 | |
102 18.62745098 | |
103 18.44660194 | |
104 18.26923077 | |
105 18.09523810 | |
106 17.92452830 | |
107 17.75700935 | |
108 17.59259259 | |
109 17.43119266 | |
110 17.27272727 | |
111 17.11711712 | |
112 16.96428571 | |
113 16.81415929 | |
114 16.66666667 | |
115 16.52173913 | |
116 16.37931034 | |
117 17.09401709 | |
118 16.94915254 | |
119 16.80672269 | |
120 17.50000000 | |
121 18.18181818 | |
122 18.03278689 | |
123 17.88617886 | |
124 17.74193548 | |
125 17.60000000 | |
126 18.25396825 | |
127 18.11023622 | |
128 18.75000000 | |
129 19.37984496 | |
130 19.23076923 | |
131 19.08396947 | |
132 18.93939394 | |
133 18.79699248 | |
134 18.65671642 | |
135 18.51851852 | |
136 18.38235294 | |
137 18.24817518 | |
138 18.11594203 | |
139 17.98561151 | |
140 17.85714286 | |
141 17.73049645 | |
142 17.60563380 | |
143 17.48251748 | |
144 17.36111111 | |
145 17.24137931 | |
146 17.12328767 | |
147 17.00680272 | |
148 16.89189189 | |
149 16.77852349 | |
150 16.66666667 | |
151 16.55629139 | |
152 16.44736842 | |
153 16.33986928 | |
154 16.23376623 | |
155 16.12903226 | |
156 16.02564103 | |
157 15.92356688 | |
158 15.82278481 | |
159 15.72327044 | |
160 15.62500000 | |
161 15.52795031 | |
162 16.04938272 | |
163 15.95092025 | |
164 16.46341463 | |
165 16.36363636 | |
166 16.26506024 | |
167 16.16766467 | |
168 16.07142857 | |
169 15.97633136 | |
170 16.47058824 | |
171 16.37426901 | |
172 16.27906977 | |
173 16.18497110 | |
174 16.09195402 | |
175 16.00000000 | |
176 15.90909091 | |
177 15.81920904 | |
178 15.73033708 | |
179 15.64245810 | |
180 15.55555556 | |
181 15.46961326 | |
182 15.38461538 | |
183 15.30054645 | |
184 15.21739130 | |
185 15.67567568 | |
186 15.59139785 | |
187 15.50802139 | |
188 15.42553191 | |
189 15.34391534 | |
190 15.26315789 | |
191 15.18324607 | |
192 15.10416667 | |
193 15.02590674 | |
194 14.94845361 | |
195 14.87179487 | |
196 14.79591837 | |
197 14.72081218 | |
198 15.15151515 | |
199 15.07537688 | |
200 15.00000000 | |
201 14.92537313 | |
202 14.85148515 | |
203 15.27093596 | |
204 15.68627451 | |
205 16.09756098 | |
206 16.01941748 | |
207 15.94202899 | |
208 15.86538462 | |
209 15.78947368 | |
210 16.19047619 | |
211 16.11374408 | |
212 16.03773585 | |
213 15.96244131 | |
214 15.88785047 | |
215 16.27906977 | |
216 16.66666667 | |
217 16.58986175 | |
218 16.97247706 | |
219 16.89497717 | |
220 17.27272727 | |
221 17.19457014 | |
222 17.11711712 | |
223 17.04035874 | |
224 16.96428571 | |
225 16.88888889 | |
226 17.25663717 | |
227 17.18061674 | |
228 17.10526316 | |
229 17.46724891 | |
230 17.39130435 | |
231 17.31601732 | |
232 17.24137931 | |
233 17.16738197 | |
234 17.09401709 | |
235 17.02127660 | |
236 16.94915254 | |
237 17.29957806 | |
238 17.22689076 | |
239 17.15481172 | |
240 17.08333333 | |
241 17.42738589 | |
242 17.35537190 | |
243 17.28395062 | |
244 17.21311475 | |
245 17.14285714 | |
246 17.07317073 | |
247 17.00404858 | |
248 17.33870968 | |
249 17.26907631 | |
250 17.20000000 | |
251 17.52988048 | |
252 17.85714286 | |
253 17.78656126 | |
254 18.11023622 | |
255 18.03921569 | |
256 18.35937500 | |
257 18.67704280 | |
258 18.60465116 | |
259 18.53281853 | |
260 18.46153846 | |
261 18.39080460 | |
262 18.70229008 | |
263 18.63117871 | |
264 18.56060606 | |
265 18.49056604 | |
266 18.79699248 | |
267 18.72659176 | |
268 18.65671642 | |
269 18.58736059 | |
270 18.51851852 | |
271 18.81918819 | |
272 18.75000000 | |
273 18.68131868 | |
274 18.61313869 | |
275 18.54545455 | |
276 18.47826087 | |
277 18.41155235 | |
278 18.70503597 | |
279 18.63799283 | |
280 18.57142857 | |
281 18.86120996 | |
282 18.79432624 | |
283 18.72791519 | |
284 18.66197183 | |
285 18.59649123 | |
286 18.53146853 | |
287 18.46689895 | |
288 18.40277778 | |
289 18.33910035 | |
290 18.62068966 | |
291 18.55670103 | |
292 18.83561644 | |
293 19.11262799 | |
294 19.04761905 | |
295 18.98305085 | |
296 18.91891892 | |
297 18.85521886 | |
298 18.79194631 | |
299 18.72909699 | |
300 18.66666667 | |
301 18.60465116 | |
302 18.54304636 | |
303 18.48184818 | |
304 18.42105263 | |
305 18.68852459 | |
306 18.95424837 | |
307 18.89250814 | |
308 18.83116883 | |
309 19.09385113 | |
310 19.03225806 | |
311 19.29260450 | |
312 19.55128205 | |
313 19.80830671 | |
314 19.74522293 | |
315 20.00000000 | |
316 19.93670886 | |
317 19.87381703 | |
318 19.81132075 | |
319 20.06269592 | |
320 20.00000000 | |
321 20.24922118 | |
322 20.49689441 | |
323 20.43343653 | |
324 20.37037037 | |
325 20.30769231 | |
326 20.55214724 | |
327 20.79510703 | |
328 20.73170732 | |
329 20.66869301 | |
330 20.90909091 | |
331 20.84592145 | |
332 20.78313253 | |
333 20.72072072 | |
334 20.65868263 | |
335 20.59701493 | |
336 20.53571429 | |
337 20.47477745 | |
338 20.41420118 | |
339 20.64896755 | |
340 20.58823529 | |
341 20.52785924 | |
342 20.46783626 | |
343 20.40816327 | |
344 20.34883721 | |
345 20.28985507 | |
346 20.52023121 | |
347 20.46109510 | |
348 20.40229885 | |
349 20.34383954 | |
350 20.28571429 | |
351 20.51282051 | |
352 20.45454545 | |
353 20.39660057 | |
354 20.62146893 | |
355 20.56338028 | |
356 20.50561798 | |
357 20.44817927 | |
358 20.67039106 | |
359 20.89136490 | |
360 21.11111111 | |
361 21.32963989 | |
362 21.27071823 | |
363 21.21212121 | |
364 21.15384615 | |
365 21.09589041 | |
366 21.03825137 | |
367 20.98092643 | |
368 20.92391304 | |
369 20.86720867 | |
370 20.81081081 | |
371 20.75471698 | |
372 20.69892473 | |
373 20.64343164 | |
374 20.58823529 | |
375 20.80000000 | |
376 20.74468085 | |
377 20.68965517 | |
378 20.63492063 | |
379 20.58047493 | |
380 20.52631579 | |
381 20.47244094 | |
382 20.41884817 | |
383 20.36553525 | |
384 20.31250000 | |
385 20.25974026 | |
386 20.20725389 | |
387 20.15503876 | |
388 20.10309278 | |
389 20.05141388 | |
390 20.00000000 | |
391 20.20460358 | |
392 20.15306122 | |
393 20.10178117 | |
394 20.05076142 | |
395 20.00000000 | |
396 19.94949495 | |
397 19.89924433 | |
398 19.84924623 | |
399 19.79949875 | |
400 19.75000000 | |
401 19.95012469 | |
402 19.90049751 | |
403 20.09925558 | |
404 20.29702970 | |
405 20.24691358 | |
406 20.19704433 | |
407 20.14742015 | |
408 20.09803922 | |
409 20.04889976 | |
410 20.00000000 | |
411 19.95133820 | |
412 19.90291262 | |
413 19.85472155 | |
414 19.80676329 | |
415 20.00000000 | |
416 19.95192308 | |
417 19.90407674 | |
418 19.85645933 | |
419 19.80906921 | |
420 19.76190476 | |
421 19.95249406 | |
422 19.90521327 | |
423 20.09456265 | |
424 20.04716981 | |
425 20.23529412 | |
426 20.18779343 | |
427 20.14051522 | |
428 20.32710280 | |
429 20.27972028 | |
430 20.23255814 | |
431 20.18561485 | |
432 20.13888889 | |
433 20.32332564 | |
434 20.27649770 | |
435 20.45977011 | |
436 20.41284404 | |
437 20.36613272 | |
438 20.54794521 | |
439 20.50113895 | |
440 20.68181818 | |
441 20.86167800 | |
442 20.81447964 | |
443 20.76749436 | |
444 20.94594595 | |
445 20.89887640 | |
446 20.85201794 | |
447 20.80536913 | |
448 20.75892857 | |
449 20.71269488 | |
450 20.66666667 | |
451 20.62084257 | |
452 20.57522124 | |
453 20.52980132 | |
454 20.48458150 | |
455 20.65934066 | |
456 20.83333333 | |
457 20.78774617 | |
458 20.74235808 | |
459 20.69716776 | |
460 20.65217391 | |
461 20.60737527 | |
462 20.56277056 | |
463 20.51835853 | |
464 20.47413793 | |
465 20.43010753 | |
466 20.38626609 | |
467 20.34261242 | |
468 20.29914530 | |
469 20.25586354 | |
470 20.21276596 | |
471 20.38216561 | |
472 20.33898305 | |
473 20.29598309 | |
474 20.25316456 | |
475 20.21052632 | |
476 20.16806723 | |
477 20.12578616 | |
478 20.08368201 | |
479 20.04175365 | |
480 20.00000000 | |
481 19.95841996 | |
482 19.91701245 | |
483 19.87577640 | |
484 20.04132231 | |
485 20.20618557 | |
486 20.16460905 | |
487 20.12320329 | |
488 20.08196721 | |
489 20.04089980 | |
490 20.00000000 | |
491 19.95926680 | |
492 20.12195122 | |
493 20.08113590 | |
494 20.24291498 | |
495 20.40404040 | |
496 20.36290323 | |
497 20.32193159 | |
498 20.48192771 | |
499 20.64128257 | |
500 20.60000000 | |
501 20.55888224 | |
502 20.71713147 | |
503 20.67594433 | |
504 20.63492063 | |
505 20.59405941 | |
506 20.55335968 | |
507 20.51282051 | |
508 20.47244094 | |
509 20.43222004 | |
510 20.39215686 | |
511 20.35225049 | |
512 20.31250000 | |
513 20.46783626 | |
514 20.42801556 | |
515 20.58252427 | |
516 20.54263566 | |
517 20.50290135 | |
518 20.46332046 | |
519 20.42389210 | |
520 20.57692308 | |
521 20.53742802 | |
522 20.49808429 | |
523 20.45889101 | |
524 20.41984733 | |
525 20.38095238 | |
526 20.34220532 | |
527 20.30360531 | |
528 20.45454545 | |
529 20.41587902 | |
530 20.37735849 | |
531 20.33898305 | |
532 20.30075188 | |
533 20.45028143 | |
534 20.41198502 | |
535 20.37383178 | |
536 20.52238806 | |
537 20.48417132 | |
538 20.44609665 | |
539 20.59369202 | |
540 20.55555556 | |
541 20.51756007 | |
542 20.66420664 | |
543 20.62615101 | |
544 20.77205882 | |
545 20.73394495 | |
546 20.87912088 | |
547 20.84095064 | |
548 20.98540146 | |
549 20.94717668 | |
550 20.90909091 | |
551 21.05263158 | |
552 21.01449275 | |
553 21.15732369 | |
554 21.11913357 | |
555 21.08108108 | |
556 21.04316547 | |
557 21.00538600 | |
558 20.96774194 | |
559 20.93023256 | |
560 20.89285714 | |
561 20.85561497 | |
562 20.81850534 | |
563 20.78152753 | |
564 20.92198582 | |
565 20.88495575 | |
566 20.84805654 | |
567 20.81128748 | |
568 20.77464789 | |
569 20.73813708 | |
570 20.70175439 | |
571 20.66549912 | |
572 20.62937063 | |
573 20.76788831 | |
574 20.73170732 | |
575 20.69565217 | |
576 20.65972222 | |
577 20.79722704 | |
578 20.76124567 | |
579 20.72538860 | |
580 20.68965517 | |
581 20.65404475 | |
582 20.61855670 | |
583 20.58319039 | |
584 20.54794521 | |
585 20.51282051 | |
586 20.47781570 | |
587 20.44293015 | |
588 20.40816327 | |
589 20.37351443 | |
590 20.33898305 | |
591 20.47377327 | |
592 20.43918919 | |
593 20.40472175 | |
594 20.37037037 | |
595 20.33613445 | |
596 20.30201342 | |
597 20.26800670 | |
598 20.40133779 | |
599 20.53422371 | |
600 20.66666667 | |
601 20.63227953 | |
602 20.59800664 | |
603 20.56384743 | |
604 20.52980132 | |
605 20.49586777 | |
606 20.46204620 | |
607 20.42833608 | |
608 20.39473684 | |
609 20.36124795 | |
610 20.49180328 | |
611 20.45826514 | |
612 20.58823529 | |
613 20.55464927 | |
614 20.52117264 | |
615 20.48780488 | |
616 20.45454545 | |
617 20.42139384 | |
618 20.38834951 | |
619 20.51696284 | |
620 20.48387097 | |
621 20.45088567 | |
622 20.41800643 | |
623 20.38523274 | |
624 20.35256410 | |
625 20.32000000 | |
626 20.28753994 | |
627 20.25518341 | |
628 20.22292994 | |
629 20.19077901 | |
630 20.15873016 | |
631 20.12678288 | |
632 20.09493671 | |
633 20.06319115 | |
634 20.18927445 | |
635 20.15748031 | |
636 20.12578616 | |
637 20.09419152 | |
638 20.06269592 | |
639 20.03129890 | |
640 20.00000000 | |
641 19.96879875 | |
642 19.93769470 | |
643 19.90668740 | |
644 19.87577640 | |
645 19.84496124 | |
646 19.81424149 | |
647 19.78361669 | |
648 19.75308642 | |
649 19.87673344 | |
650 19.84615385 | |
651 19.81566820 | |
652 19.78527607 | |
653 19.75497703 | |
654 19.72477064 | |
655 19.69465649 | |
656 19.66463415 | |
657 19.63470320 | |
658 19.60486322 | |
659 19.57511381 | |
660 19.54545455 | |
661 19.51588502 | |
662 19.48640483 | |
663 19.45701357 | |
664 19.42771084 | |
665 19.39849624 | |
666 19.36936937 | |
667 19.34032984 | |
668 19.31137725 | |
669 19.28251121 | |
670 19.25373134 | |
671 19.37406855 | |
672 19.34523810 | |
673 19.31649331 | |
674 19.43620178 | |
675 19.40740741 | |
676 19.52662722 | |
677 19.49778434 | |
678 19.61651917 | |
679 19.58762887 | |
680 19.55882353 | |
681 19.67694567 | |
682 19.64809384 | |
683 19.61932650 | |
684 19.59064327 | |
685 19.70802920 | |
686 19.67930029 | |
687 19.65065502 | |
688 19.62209302 | |
689 19.59361393 | |
690 19.56521739 | |
691 19.53690304 | |
692 19.50867052 | |
693 19.48051948 | |
694 19.45244957 | |
695 19.42446043 | |
696 19.39655172 | |
697 19.36872310 | |
698 19.34097421 | |
699 19.31330472 | |
700 19.42857143 | |
701 19.54350927 | |
702 19.51566952 | |
703 19.48790896 | |
704 19.46022727 | |
705 19.43262411 | |
706 19.54674221 | |
707 19.51909477 | |
708 19.49152542 | |
709 19.46403385 | |
710 19.43661972 | |
711 19.54992968 | |
712 19.66292135 | |
713 19.63534362 | |
714 19.60784314 | |
715 19.58041958 | |
716 19.55307263 | |
717 19.52580195 | |
718 19.49860724 | |
719 19.47148818 | |
720 19.44444444 | |
721 19.41747573 | |
722 19.52908587 | |
723 19.50207469 | |
724 19.61325967 | |
725 19.58620690 | |
726 19.69696970 | |
727 19.66987620 | |
728 19.78021978 | |
729 19.75308642 | |
730 19.86301370 | |
731 19.83584131 | |
732 19.80874317 | |
733 19.78171896 | |
734 19.75476839 | |
735 19.72789116 | |
736 19.70108696 | |
737 19.67435550 | |
738 19.78319783 | |
739 19.75642760 | |
740 19.86486486 | |
741 19.83805668 | |
742 19.81132075 | |
743 19.91924630 | |
744 20.02688172 | |
745 20.00000000 | |
746 19.97319035 | |
747 20.08032129 | |
748 20.05347594 | |
749 20.16021362 | |
750 20.13333333 | |
751 20.10652463 | |
752 20.07978723 | |
753 20.05312085 | |
754 20.15915119 | |
755 20.26490066 | |
756 20.23809524 | |
757 20.21136063 | |
758 20.18469657 | |
759 20.15810277 | |
760 20.26315789 | |
761 20.36793693 | |
762 20.34120735 | |
763 20.31454784 | |
764 20.28795812 | |
765 20.26143791 | |
766 20.36553525 | |
767 20.46936115 | |
768 20.44270833 | |
769 20.41612484 | |
770 20.38961039 | |
771 20.36316472 | |
772 20.33678756 | |
773 20.31047865 | |
774 20.28423773 | |
775 20.25806452 | |
776 20.23195876 | |
777 20.20592021 | |
778 20.17994859 | |
779 20.15404365 | |
780 20.25641026 | |
781 20.23047375 | |
782 20.33248082 | |
783 20.30651341 | |
784 20.28061224 | |
785 20.25477707 | |
786 20.22900763 | |
787 20.20330368 | |
788 20.17766497 | |
789 20.27883397 | |
Final result: 20.2788 +/- 1.4323 | |
Random chance: 10.1310 +/- 1.0749 | |