DeepSeek-R1-Distill-Qwen-7B-GGUF / scores /deepseek-r1-distill-qwen-7b-f16.tqa
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
94d6d71 verified
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 817 tasks in prompt
multiple_choice_score: selecting 750 random tasks from 817 tasks available
multiple_choice_score: preparing task data...done
multiple_choice_score : calculating TruthfulQA score over 750 tasks.
task acc_norm
1 100.00000000
2 50.00000000
3 33.33333333
4 25.00000000
5 20.00000000
6 16.66666667
7 14.28571429
8 12.50000000
9 11.11111111
10 10.00000000
11 9.09090909
12 16.66666667
13 15.38461538
14 14.28571429
15 13.33333333
16 12.50000000
17 17.64705882
18 16.66666667
19 21.05263158
20 20.00000000
21 19.04761905
22 18.18181818
23 17.39130435
24 20.83333333
25 20.00000000
26 23.07692308
27 22.22222222
28 21.42857143
29 24.13793103
30 23.33333333
31 25.80645161
32 25.00000000
33 27.27272727
34 26.47058824
35 25.71428571
36 25.00000000
37 27.02702703
38 26.31578947
39 25.64102564
40 25.00000000
41 24.39024390
42 23.80952381
43 25.58139535
44 25.00000000
45 24.44444444
46 26.08695652
47 25.53191489
48 27.08333333
49 26.53061224
50 28.00000000
51 27.45098039
52 26.92307692
53 28.30188679
54 29.62962963
55 30.90909091
56 30.35714286
57 29.82456140
58 29.31034483
59 28.81355932
60 30.00000000
61 29.50819672
62 30.64516129
63 30.15873016
64 29.68750000
65 29.23076923
66 28.78787879
67 28.35820896
68 27.94117647
69 27.53623188
70 27.14285714
71 28.16901408
72 29.16666667
73 30.13698630
74 29.72972973
75 29.33333333
76 30.26315789
77 29.87012987
78 29.48717949
79 29.11392405
80 28.75000000
81 28.39506173
82 28.04878049
83 27.71084337
84 27.38095238
85 27.05882353
86 26.74418605
87 26.43678161
88 26.13636364
89 26.96629213
90 26.66666667
91 26.37362637
92 26.08695652
93 25.80645161
94 25.53191489
95 26.31578947
96 27.08333333
97 26.80412371
98 26.53061224
99 27.27272727
100 27.00000000
101 27.72277228
102 27.45098039
103 28.15533981
104 27.88461538
105 27.61904762
106 27.35849057
107 28.03738318
108 28.70370370
109 28.44036697
110 29.09090909
111 28.82882883
112 28.57142857
113 28.31858407
114 28.07017544
115 27.82608696
116 27.58620690
117 27.35042735
118 27.11864407
119 26.89075630
120 26.66666667
121 27.27272727
122 27.04918033
123 26.82926829
124 27.41935484
125 28.00000000
126 28.57142857
127 28.34645669
128 28.12500000
129 27.90697674
130 27.69230769
131 27.48091603
132 27.27272727
133 27.06766917
134 27.61194030
135 27.40740741
136 27.20588235
137 27.73722628
138 27.53623188
139 28.05755396
140 27.85714286
141 27.65957447
142 27.46478873
143 27.27272727
144 27.08333333
145 26.89655172
146 26.71232877
147 26.53061224
148 26.35135135
149 26.17449664
150 26.00000000
151 26.49006623
152 26.31578947
153 26.14379085
154 25.97402597
155 25.80645161
156 26.28205128
157 26.11464968
158 26.58227848
159 26.41509434
160 26.25000000
161 26.08695652
162 25.92592593
163 25.76687117
164 25.60975610
165 26.06060606
166 26.50602410
167 26.34730539
168 26.19047619
169 26.03550296
170 25.88235294
171 25.73099415
172 25.58139535
173 25.43352601
174 25.28735632
175 25.14285714
176 25.56818182
177 25.42372881
178 25.28089888
179 25.13966480
180 25.00000000
181 24.86187845
182 24.72527473
183 24.59016393
184 24.45652174
185 24.32432432
186 24.73118280
187 24.59893048
188 24.46808511
189 24.86772487
190 24.73684211
191 24.60732984
192 24.47916667
193 24.35233161
194 24.74226804
195 24.61538462
196 24.48979592
197 24.87309645
198 25.25252525
199 25.12562814
200 25.00000000
201 24.87562189
202 25.24752475
203 25.12315271
204 25.00000000
205 25.36585366
206 25.24271845
207 25.60386473
208 25.48076923
209 25.35885167
210 25.23809524
211 25.11848341
212 25.00000000
213 24.88262911
214 24.76635514
215 24.65116279
216 25.00000000
217 24.88479263
218 25.22935780
219 25.11415525
220 25.00000000
221 24.88687783
222 24.77477477
223 24.66367713
224 25.00000000
225 24.88888889
226 24.77876106
227 24.66960352
228 24.56140351
229 24.45414847
230 24.34782609
231 24.24242424
232 24.56896552
233 24.89270386
234 24.78632479
235 24.68085106
236 25.00000000
237 25.31645570
238 25.63025210
239 25.52301255
240 25.41666667
241 25.31120332
242 25.20661157
243 25.10288066
244 25.00000000
245 24.89795918
246 24.79674797
247 24.69635628
248 24.59677419
249 24.49799197
250 24.40000000
251 24.70119522
252 24.60317460
253 24.50592885
254 24.40944882
255 24.31372549
256 24.21875000
257 24.12451362
258 24.03100775
259 23.93822394
260 23.84615385
261 24.13793103
262 24.04580153
263 23.95437262
264 24.24242424
265 24.52830189
266 24.43609023
267 24.71910112
268 24.62686567
269 24.53531599
270 24.44444444
271 24.35424354
272 24.26470588
273 24.17582418
274 24.08759124
275 24.00000000
276 23.91304348
277 23.82671480
278 23.74100719
279 23.65591398
280 23.57142857
281 23.84341637
282 23.75886525
283 23.67491166
284 23.94366197
285 23.85964912
286 24.12587413
287 24.04181185
288 23.95833333
289 23.87543253
290 23.79310345
291 24.05498282
292 24.31506849
293 24.57337884
294 24.48979592
295 24.74576271
296 25.00000000
297 25.25252525
298 25.16778523
299 25.08361204
300 25.00000000
301 24.91694352
302 24.83443709
303 24.75247525
304 24.67105263
305 24.59016393
306 24.50980392
307 24.42996743
308 24.67532468
309 24.59546926
310 24.51612903
311 24.43729904
312 24.67948718
313 24.60063898
314 24.52229299
315 24.44444444
316 24.36708861
317 24.29022082
318 24.21383648
319 24.13793103
320 24.06250000
321 23.98753894
322 24.22360248
323 24.14860681
324 24.07407407
325 24.00000000
326 23.92638037
327 23.85321101
328 24.08536585
329 24.01215805
330 24.24242424
331 24.16918429
332 24.39759036
333 24.32432432
334 24.25149701
335 24.47761194
336 24.70238095
337 24.62908012
338 24.55621302
339 24.77876106
340 24.70588235
341 24.92668622
342 25.14619883
343 25.07288630
344 25.29069767
345 25.50724638
346 25.72254335
347 25.93659942
348 25.86206897
349 25.78796562
350 25.71428571
351 25.64102564
352 25.85227273
353 25.77903683
354 25.70621469
355 25.91549296
356 25.84269663
357 25.77030812
358 25.97765363
359 25.90529248
360 25.83333333
361 25.76177285
362 25.69060773
363 25.89531680
364 25.82417582
365 26.02739726
366 25.95628415
367 26.15803815
368 26.08695652
369 26.01626016
370 25.94594595
371 25.87601078
372 26.07526882
373 26.00536193
374 26.20320856
375 26.13333333
376 26.06382979
377 25.99469496
378 25.92592593
379 25.85751979
380 25.78947368
381 25.72178478
382 25.65445026
383 25.58746736
384 25.52083333
385 25.45454545
386 25.38860104
387 25.32299742
388 25.51546392
389 25.44987147
390 25.38461538
391 25.57544757
392 25.51020408
393 25.44529262
394 25.63451777
395 25.56962025
396 25.50505051
397 25.69269521
398 25.62814070
399 25.56390977
400 25.50000000
401 25.43640898
402 25.37313433
403 25.55831266
404 25.49504950
405 25.43209877
406 25.36945813
407 25.30712531
408 25.24509804
409 25.18337408
410 25.12195122
411 25.06082725
412 25.24271845
413 25.18159806
414 25.36231884
415 25.30120482
416 25.24038462
417 25.17985612
418 25.11961722
419 25.05966587
420 25.23809524
421 25.41567696
422 25.35545024
423 25.29550827
424 25.23584906
425 25.17647059
426 25.11737089
427 25.05854801
428 25.00000000
429 24.94172494
430 24.88372093
431 24.82598608
432 25.00000000
433 25.17321016
434 25.34562212
435 25.28735632
436 25.22935780
437 25.17162471
438 25.11415525
439 25.05694761
440 25.22727273
441 25.17006803
442 25.33936652
443 25.28216704
444 25.22522523
445 25.16853933
446 25.11210762
447 25.05592841
448 25.00000000
449 25.16703786
450 25.11111111
451 25.05543237
452 25.00000000
453 25.16556291
454 25.11013216
455 25.05494505
456 25.00000000
457 24.94529540
458 24.89082969
459 24.83660131
460 24.78260870
461 24.72885033
462 24.67532468
463 24.62203024
464 24.56896552
465 24.73118280
466 24.67811159
467 24.62526767
468 24.57264957
469 24.52025586
470 24.46808511
471 24.41613588
472 24.36440678
473 24.31289641
474 24.26160338
475 24.42105263
476 24.36974790
477 24.52830189
478 24.47698745
479 24.42588727
480 24.37500000
481 24.32432432
482 24.48132780
483 24.43064182
484 24.58677686
485 24.74226804
486 24.69135802
487 24.84599589
488 24.79508197
489 24.94887526
490 25.10204082
491 25.05091650
492 25.20325203
493 25.15212982
494 25.10121457
495 25.25252525
496 25.20161290
497 25.15090543
498 25.10040161
499 25.05010020
500 25.00000000
501 25.14970060
502 25.09960159
503 25.04970179
504 25.19841270
505 25.14851485
506 25.09881423
507 25.04930966
508 25.00000000
509 25.14734774
510 25.29411765
511 25.24461840
512 25.19531250
513 25.14619883
514 25.09727626
515 25.24271845
516 25.19379845
517 25.33849130
518 25.28957529
519 25.24084778
520 25.19230769
521 25.33589251
522 25.28735632
523 25.43021033
524 25.38167939
525 25.33333333
526 25.28517110
527 25.42694497
528 25.56818182
529 25.51984877
530 25.47169811
531 25.61205273
532 25.56390977
533 25.70356473
534 25.65543071
535 25.60747664
536 25.55970149
537 25.69832402
538 25.65055762
539 25.60296846
540 25.74074074
541 25.69316081
542 25.64575646
543 25.59852670
544 25.55147059
545 25.50458716
546 25.64102564
547 25.59414991
548 25.72992701
549 25.68306011
550 25.63636364
551 25.58983666
552 25.72463768
553 25.67811935
554 25.63176895
555 25.58558559
556 25.71942446
557 25.67324955
558 25.62724014
559 25.58139535
560 25.53571429
561 25.49019608
562 25.44483986
563 25.39964476
564 25.53191489
565 25.66371681
566 25.61837456
567 25.57319224
568 25.70422535
569 25.83479789
570 25.78947368
571 25.74430823
572 25.69930070
573 25.65445026
574 25.78397213
575 25.91304348
576 25.86805556
577 25.82322357
578 25.95155709
579 26.07944732
580 26.20689655
581 26.16179002
582 26.28865979
583 26.24356775
584 26.36986301
585 26.32478632
586 26.45051195
587 26.40545145
588 26.36054422
589 26.31578947
590 26.44067797
591 26.39593909
592 26.35135135
593 26.30691400
594 26.26262626
595 26.21848739
596 26.17449664
597 26.29815745
598 26.25418060
599 26.21035058
600 26.16666667
601 26.28951747
602 26.41196013
603 26.36815920
604 26.32450331
605 26.28099174
606 26.40264026
607 26.35914333
608 26.31578947
609 26.27257800
610 26.22950820
611 26.18657938
612 26.30718954
613 26.26427406
614 26.22149837
615 26.17886179
616 26.29870130
617 26.41815235
618 26.37540453
619 26.49434572
620 26.45161290
621 26.40901771
622 26.52733119
623 26.48475120
624 26.44230769
625 26.40000000
626 26.35782748
627 26.31578947
628 26.27388535
629 26.23211447
630 26.19047619
631 26.30744849
632 26.42405063
633 26.38230648
634 26.49842271
635 26.45669291
636 26.41509434
637 26.37362637
638 26.33228840
639 26.29107981
640 26.25000000
641 26.20904836
642 26.32398754
643 26.28304821
644 26.39751553
645 26.51162791
646 26.47058824
647 26.42967543
648 26.54320988
649 26.50231125
650 26.61538462
651 26.72811060
652 26.84049080
653 26.95252680
654 26.91131498
655 26.87022901
656 26.82926829
657 26.94063927
658 26.89969605
659 26.85887709
660 26.81818182
661 26.77760968
662 26.73716012
663 26.69683258
664 26.65662651
665 26.76691729
666 26.87687688
667 26.83658171
668 26.79640719
669 26.75635277
670 26.71641791
671 26.67660209
672 26.63690476
673 26.59732541
674 26.55786350
675 26.66666667
676 26.77514793
677 26.73559823
678 26.69616519
679 26.65684831
680 26.76470588
681 26.72540382
682 26.68621701
683 26.64714495
684 26.75438596
685 26.71532847
686 26.67638484
687 26.63755459
688 26.74418605
689 26.85050798
690 26.81159420
691 26.91751085
692 26.87861272
693 26.83982684
694 26.94524496
695 26.90647482
696 27.01149425
697 26.97274032
698 26.93409742
699 27.03862661
700 27.14285714
701 27.10413695
702 27.06552707
703 27.02702703
704 26.98863636
705 26.95035461
706 26.91218130
707 26.87411598
708 26.83615819
709 26.79830748
710 26.76056338
711 26.72292546
712 26.82584270
713 26.78821879
714 26.75070028
715 26.71328671
716 26.67597765
717 26.63877266
718 26.60167131
719 26.56467316
720 26.52777778
721 26.49098474
722 26.45429363
723 26.41770401
724 26.38121547
725 26.34482759
726 26.44628099
727 26.40990371
728 26.37362637
729 26.33744856
730 26.43835616
731 26.40218878
732 26.50273224
733 26.46657572
734 26.43051771
735 26.39455782
736 26.35869565
737 26.32293080
738 26.28726287
739 26.38700947
740 26.35135135
741 26.31578947
742 26.28032345
743 26.24495289
744 26.34408602
745 26.30872483
746 26.40750670
747 26.50602410
748 26.47058824
749 26.56875834
750 26.66666667
Final result: 26.6667 ±1.6158
Random chance: 19.8992 ±1.4588