DeepSeek-R1-Distill-Llama-8B-GGUF / scores /DeepSeek-R1-Distill-Llama-8B-iq3_s.arc
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
afa61ba verified
raw
history blame
12.6 kB
common_init_from_params: setting dry_penalty_last_n to ctx_size = 768
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 6 (n_threads_batch = 6) / 12 | Metal : EMBED_LIBRARY = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | LLAMAFILE = 1 | ACCELERATE = 1 | AARCH64_REPACK = 1 |
multiple_choice_score: there are 869 tasks in prompt
multiple_choice_score: selecting 750 random tasks from 869 tasks available
multiple_choice_score: preparing task data...done
multiple_choice_score : calculating TruthfulQA score over 750 tasks.
task acc_norm
1 0.00000000
2 50.00000000
3 33.33333333
4 25.00000000
5 40.00000000
6 50.00000000
7 57.14285714
8 50.00000000
9 44.44444444
10 50.00000000
11 45.45454545
12 50.00000000
13 46.15384615
14 42.85714286
15 46.66666667
16 43.75000000
17 47.05882353
18 50.00000000
19 47.36842105
20 45.00000000
21 47.61904762
22 50.00000000
23 47.82608696
24 50.00000000
25 48.00000000
26 46.15384615
27 48.14814815
28 46.42857143
29 48.27586207
30 50.00000000
31 48.38709677
32 50.00000000
33 48.48484848
34 47.05882353
35 45.71428571
36 44.44444444
37 45.94594595
38 44.73684211
39 43.58974359
40 45.00000000
41 43.90243902
42 45.23809524
43 44.18604651
44 43.18181818
45 44.44444444
46 45.65217391
47 46.80851064
48 45.83333333
49 44.89795918
50 46.00000000
51 47.05882353
52 48.07692308
53 49.05660377
54 48.14814815
55 47.27272727
56 46.42857143
57 47.36842105
58 48.27586207
59 49.15254237
60 50.00000000
61 50.81967213
62 51.61290323
63 52.38095238
64 53.12500000
65 52.30769231
66 53.03030303
67 53.73134328
68 54.41176471
69 53.62318841
70 52.85714286
71 52.11267606
72 51.38888889
73 52.05479452
74 51.35135135
75 52.00000000
76 51.31578947
77 50.64935065
78 51.28205128
79 50.63291139
80 50.00000000
81 49.38271605
82 50.00000000
83 49.39759036
84 48.80952381
85 49.41176471
86 48.83720930
87 48.27586207
88 48.86363636
89 49.43820225
90 50.00000000
91 50.54945055
92 51.08695652
93 50.53763441
94 50.00000000
95 50.52631579
96 51.04166667
97 50.51546392
98 50.00000000
99 50.50505051
100 50.00000000
101 49.50495050
102 50.00000000
103 49.51456311
104 50.00000000
105 50.47619048
106 50.00000000
107 50.46728972
108 50.00000000
109 49.54128440
110 50.00000000
111 50.45045045
112 50.89285714
113 50.44247788
114 50.00000000
115 50.43478261
116 50.86206897
117 51.28205128
118 51.69491525
119 51.26050420
120 51.66666667
121 51.23966942
122 51.63934426
123 52.03252033
124 51.61290323
125 52.00000000
126 52.38095238
127 51.96850394
128 52.34375000
129 51.93798450
130 51.53846154
131 51.90839695
132 51.51515152
133 51.87969925
134 51.49253731
135 51.11111111
136 50.73529412
137 51.09489051
138 51.44927536
139 51.07913669
140 50.71428571
141 50.35460993
142 50.70422535
143 51.04895105
144 50.69444444
145 51.03448276
146 50.68493151
147 51.02040816
148 50.67567568
149 51.00671141
150 51.33333333
151 51.65562914
152 51.97368421
153 51.63398693
154 51.29870130
155 50.96774194
156 51.28205128
157 50.95541401
158 50.63291139
159 50.94339623
160 50.62500000
161 50.31055901
162 50.00000000
163 50.30674847
164 50.00000000
165 49.69696970
166 50.00000000
167 49.70059880
168 50.00000000
169 49.70414201
170 49.41176471
171 49.70760234
172 50.00000000
173 50.28901734
174 50.00000000
175 49.71428571
176 49.43181818
177 49.71751412
178 50.00000000
179 49.72067039
180 49.44444444
181 49.17127072
182 49.45054945
183 49.18032787
184 48.91304348
185 49.18918919
186 49.46236559
187 49.73262032
188 49.46808511
189 49.20634921
190 48.94736842
191 49.21465969
192 48.95833333
193 48.70466321
194 48.96907216
195 49.23076923
196 49.48979592
197 49.74619289
198 49.49494949
199 49.74874372
200 50.00000000
201 50.24875622
202 50.00000000
203 49.75369458
204 50.00000000
205 49.75609756
206 49.51456311
207 49.75845411
208 49.51923077
209 49.28229665
210 49.52380952
211 49.76303318
212 49.52830189
213 49.76525822
214 50.00000000
215 50.23255814
216 50.00000000
217 50.23041475
218 50.00000000
219 49.77168950
220 49.54545455
221 49.77375566
222 49.54954955
223 49.32735426
224 49.55357143
225 49.33333333
226 49.55752212
227 49.77973568
228 50.00000000
229 50.21834061
230 50.43478261
231 50.21645022
232 50.00000000
233 49.78540773
234 49.57264957
235 49.36170213
236 49.15254237
237 48.94514768
238 49.15966387
239 49.37238494
240 49.58333333
241 49.79253112
242 49.58677686
243 49.79423868
244 49.59016393
245 49.38775510
246 49.59349593
247 49.79757085
248 49.59677419
249 49.39759036
250 49.60000000
251 49.80079681
252 50.00000000
253 50.19762846
254 50.00000000
255 50.19607843
256 50.39062500
257 50.58365759
258 50.38759690
259 50.19305019
260 50.00000000
261 50.19157088
262 50.00000000
263 50.19011407
264 50.00000000
265 50.18867925
266 50.00000000
267 50.18726592
268 50.37313433
269 50.18587361
270 50.37037037
271 50.55350554
272 50.36764706
273 50.18315018
274 50.00000000
275 49.81818182
276 49.63768116
277 49.81949458
278 49.64028777
279 49.82078853
280 50.00000000
281 50.17793594
282 50.35460993
283 50.17667845
284 50.35211268
285 50.52631579
286 50.34965035
287 50.17421603
288 50.34722222
289 50.17301038
290 50.34482759
291 50.17182131
292 50.34246575
293 50.51194539
294 50.34013605
295 50.50847458
296 50.67567568
297 50.84175084
298 51.00671141
299 50.83612040
300 51.00000000
301 50.83056478
302 50.99337748
303 51.15511551
304 50.98684211
305 51.14754098
306 50.98039216
307 50.81433225
308 50.97402597
309 51.13268608
310 50.96774194
311 51.12540193
312 50.96153846
313 51.11821086
314 50.95541401
315 50.79365079
316 50.94936709
317 51.10410095
318 50.94339623
319 50.78369906
320 50.62500000
321 50.46728972
322 50.62111801
323 50.46439628
324 50.30864198
325 50.15384615
326 50.30674847
327 50.15290520
328 50.30487805
329 50.15197568
330 50.00000000
331 50.15105740
332 50.30120482
333 50.45045045
334 50.59880240
335 50.44776119
336 50.59523810
337 50.44510386
338 50.29585799
339 50.44247788
340 50.58823529
341 50.43988270
342 50.29239766
343 50.43731778
344 50.58139535
345 50.43478261
346 50.57803468
347 50.43227666
348 50.28735632
349 50.14326648
350 50.28571429
351 50.42735043
352 50.28409091
353 50.42492918
354 50.28248588
355 50.14084507
356 50.28089888
357 50.14005602
358 50.27932961
359 50.13927577
360 50.00000000
361 50.13850416
362 50.27624309
363 50.13774105
364 50.00000000
365 49.86301370
366 49.72677596
367 49.59128065
368 49.45652174
369 49.32249322
370 49.18918919
371 49.05660377
372 48.92473118
373 48.79356568
374 48.93048128
375 49.06666667
376 48.93617021
377 49.07161804
378 49.20634921
379 49.07651715
380 49.21052632
381 49.08136483
382 48.95287958
383 48.82506527
384 48.69791667
385 48.83116883
386 48.70466321
387 48.57881137
388 48.45360825
389 48.32904884
390 48.20512821
391 48.08184143
392 48.21428571
393 48.09160305
394 47.96954315
395 48.10126582
396 47.97979798
397 47.85894207
398 47.73869347
399 47.86967419
400 48.00000000
401 47.88029925
402 47.76119403
403 47.89081886
404 47.77227723
405 47.90123457
406 48.02955665
407 48.15724816
408 48.28431373
409 48.16625917
410 48.29268293
411 48.17518248
412 48.30097087
413 48.18401937
414 48.30917874
415 48.19277108
416 48.07692308
417 47.96163070
418 47.84688995
419 47.73269690
420 47.61904762
421 47.74346793
422 47.86729858
423 47.99054374
424 47.87735849
425 47.76470588
426 47.65258216
427 47.77517564
428 47.66355140
429 47.78554779
430 47.67441860
431 47.56380510
432 47.68518519
433 47.57505774
434 47.46543779
435 47.58620690
436 47.70642202
437 47.59725400
438 47.48858447
439 47.60820046
440 47.50000000
441 47.61904762
442 47.51131222
443 47.40406321
444 47.29729730
445 47.41573034
446 47.53363229
447 47.42729306
448 47.32142857
449 47.43875278
450 47.33333333
451 47.22838137
452 47.12389381
453 47.24061810
454 47.13656388
455 47.03296703
456 46.92982456
457 46.82713348
458 46.94323144
459 47.05882353
460 46.95652174
461 46.85466377
462 46.96969697
463 46.86825054
464 46.76724138
465 46.88172043
466 46.78111588
467 46.89507495
468 47.00854701
469 46.90831557
470 46.80851064
471 46.92144374
472 47.03389831
473 46.93446089
474 47.04641350
475 46.94736842
476 46.84873950
477 46.96016771
478 47.07112971
479 47.18162839
480 47.29166667
481 47.19334719
482 47.30290456
483 47.41200828
484 47.52066116
485 47.62886598
486 47.73662551
487 47.63860370
488 47.74590164
489 47.64826176
490 47.55102041
491 47.65784114
492 47.76422764
493 47.66734280
494 47.77327935
495 47.67676768
496 47.58064516
497 47.68611670
498 47.79116466
499 47.89579158
500 47.80000000
501 47.70459082
502 47.80876494
503 47.91252485
504 47.81746032
505 47.92079208
506 47.82608696
507 47.73175542
508 47.63779528
509 47.54420432
510 47.45098039
511 47.35812133
512 47.26562500
513 47.17348928
514 47.27626459
515 47.37864078
516 47.28682171
517 47.19535783
518 47.29729730
519 47.20616570
520 47.11538462
521 47.21689060
522 47.12643678
523 47.03632887
524 46.94656489
525 46.85714286
526 46.76806084
527 46.67931689
528 46.59090909
529 46.50283554
530 46.60377358
531 46.51600753
532 46.61654135
533 46.71669794
534 46.62921348
535 46.54205607
536 46.64179104
537 46.74115456
538 46.65427509
539 46.75324675
540 46.66666667
541 46.58040665
542 46.67896679
543 46.77716390
544 46.87500000
545 46.97247706
546 46.88644689
547 46.80073126
548 46.89781022
549 46.81238616
550 46.90909091
551 46.82395644
552 46.92028986
553 47.01627486
554 46.93140794
555 47.02702703
556 46.94244604
557 47.03770197
558 46.95340502
559 47.04830054
560 47.14285714
561 47.23707665
562 47.33096085
563 47.24689165
564 47.16312057
565 47.07964602
566 47.17314488
567 47.08994709
568 47.18309859
569 47.10017575
570 47.01754386
571 47.11033275
572 47.02797203
573 46.94589878
574 47.03832753
575 46.95652174
576 47.04861111
577 47.14038128
578 47.23183391
579 47.32297064
580 47.41379310
581 47.33218589
582 47.42268041
583 47.51286449
584 47.60273973
585 47.69230769
586 47.61092150
587 47.52981261
588 47.61904762
589 47.53820034
590 47.62711864
591 47.71573604
592 47.80405405
593 47.72344013
594 47.81144781
595 47.73109244
596 47.65100671
597 47.57118928
598 47.49163880
599 47.41235392
600 47.50000000
601 47.42096506
602 47.34219269
603 47.26368159
604 47.18543046
605 47.10743802
606 47.19471947
607 47.28171334
608 47.36842105
609 47.29064039
610 47.37704918
611 47.29950900
612 47.38562092
613 47.30831974
614 47.23127036
615 47.31707317
616 47.24025974
617 47.32576985
618 47.24919094
619 47.17285945
620 47.25806452
621 47.34299517
622 47.26688103
623 47.35152488
624 47.27564103
625 47.20000000
626 47.12460064
627 47.20893142
628 47.29299363
629 47.21780604
630 47.30158730
631 47.22662441
632 47.15189873
633 47.07740916
634 47.00315457
635 46.92913386
636 47.01257862
637 46.93877551
638 47.02194357
639 47.10485133
640 47.03125000
641 47.11388456
642 47.04049844
643 46.96734059
644 47.04968944
645 46.97674419
646 47.05882353
647 46.98608964
648 46.91358025
649 46.84129430
650 46.92307692
651 47.00460829
652 46.93251534
653 46.86064319
654 46.94189602
655 46.87022901
656 46.79878049
657 46.72754947
658 46.80851064
659 46.73748103
660 46.81818182
661 46.74735250
662 46.82779456
663 46.90799397
664 46.98795181
665 47.06766917
666 46.99699700
667 46.92653673
668 46.85628743
669 46.78624813
670 46.86567164
671 46.94485842
672 46.87500000
673 46.80534918
674 46.73590504
675 46.66666667
676 46.59763314
677 46.67651403
678 46.75516224
679 46.68630339
680 46.76470588
681 46.69603524
682 46.77419355
683 46.70571010
684 46.63742690
685 46.71532847
686 46.64723032
687 46.57933042
688 46.65697674
689 46.58925980
690 46.52173913
691 46.45441389
692 46.53179191
693 46.46464646
694 46.39769452
695 46.33093525
696 46.26436782
697 46.19799139
698 46.13180516
699 46.06580830
700 46.14285714
701 46.07703281
702 46.15384615
703 46.08819346
704 46.16477273
705 46.24113475
706 46.17563739
707 46.25176803
708 46.32768362
709 46.40338505
710 46.47887324
711 46.55414909
712 46.62921348
713 46.56381487
714 46.49859944
715 46.43356643
716 46.36871508
717 46.30404463
718 46.23955432
719 46.17524339
720 46.25000000
721 46.18585298
722 46.26038781
723 46.33471646
724 46.40883978
725 46.48275862
726 46.41873278
727 46.35488308
728 46.42857143
729 46.36488340
730 46.43835616
731 46.51162791
732 46.44808743
733 46.52114598
734 46.59400545
735 46.53061224
736 46.60326087
737 46.54002714
738 46.47696477
739 46.41407307
740 46.35135135
741 46.42375169
742 46.49595687
743 46.56796770
744 46.50537634
745 46.44295302
746 46.38069705
747 46.31860776
748 46.25668449
749 46.19492657
750 46.26666667
Final result: 46.2667 +/- 1.8219
Random chance: 25.0083 +/- 1.5824