DeepSeek-R1-Distill-Qwen-7B-GGUF / scores /deepseek-r1-distill-qwen-7b-iq3_s.mmlu
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
94d6d71 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 1548 tasks in prompt
multiple_choice_score: selecting 750 random tasks from 1548 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 50.00000000
5 40.00000000
6 33.33333333
7 42.85714286
8 50.00000000
9 44.44444444
10 40.00000000
11 36.36363636
12 33.33333333
13 38.46153846
14 35.71428571
15 33.33333333
16 37.50000000
17 35.29411765
18 33.33333333
19 36.84210526
20 35.00000000
21 33.33333333
22 31.81818182
23 30.43478261
24 29.16666667
25 32.00000000
26 30.76923077
27 29.62962963
28 32.14285714
29 34.48275862
30 36.66666667
31 38.70967742
32 40.62500000
33 39.39393939
34 38.23529412
35 40.00000000
36 38.88888889
37 37.83783784
38 39.47368421
39 38.46153846
40 37.50000000
41 36.58536585
42 35.71428571
43 34.88372093
44 34.09090909
45 33.33333333
46 32.60869565
47 31.91489362
48 33.33333333
49 34.69387755
50 36.00000000
51 35.29411765
52 34.61538462
53 33.96226415
54 33.33333333
55 34.54545455
56 35.71428571
57 35.08771930
58 34.48275862
59 33.89830508
60 33.33333333
61 32.78688525
62 32.25806452
63 31.74603175
64 31.25000000
65 30.76923077
66 31.81818182
67 31.34328358
68 30.88235294
69 31.88405797
70 32.85714286
71 32.39436620
72 33.33333333
73 32.87671233
74 32.43243243
75 33.33333333
76 34.21052632
77 35.06493506
78 35.89743590
79 35.44303797
80 36.25000000
81 35.80246914
82 35.36585366
83 36.14457831
84 36.90476190
85 36.47058824
86 36.04651163
87 36.78160920
88 37.50000000
89 37.07865169
90 36.66666667
91 36.26373626
92 35.86956522
93 35.48387097
94 35.10638298
95 34.73684211
96 35.41666667
97 35.05154639
98 34.69387755
99 34.34343434
100 34.00000000
101 33.66336634
102 33.33333333
103 33.00970874
104 32.69230769
105 32.38095238
106 32.07547170
107 31.77570093
108 32.40740741
109 32.11009174
110 31.81818182
111 31.53153153
112 31.25000000
113 31.85840708
114 32.45614035
115 33.04347826
116 32.75862069
117 32.47863248
118 32.20338983
119 31.93277311
120 31.66666667
121 31.40495868
122 31.14754098
123 30.89430894
124 30.64516129
125 31.20000000
126 30.95238095
127 30.70866142
128 30.46875000
129 30.23255814
130 30.00000000
131 30.53435115
132 30.30303030
133 30.07518797
134 29.85074627
135 29.62962963
136 30.14705882
137 29.92700730
138 29.71014493
139 29.49640288
140 29.28571429
141 29.07801418
142 29.57746479
143 30.06993007
144 30.55555556
145 31.03448276
146 30.82191781
147 30.61224490
148 31.08108108
149 30.87248322
150 30.66666667
151 30.46357616
152 30.92105263
153 30.71895425
154 31.16883117
155 30.96774194
156 30.76923077
157 31.21019108
158 31.64556962
159 31.44654088
160 31.87500000
161 31.67701863
162 31.48148148
163 31.28834356
164 31.09756098
165 31.51515152
166 31.32530120
167 31.73652695
168 31.54761905
169 31.36094675
170 31.17647059
171 30.99415205
172 30.81395349
173 30.63583815
174 30.45977011
175 30.28571429
176 30.68181818
177 30.50847458
178 30.33707865
179 30.72625698
180 30.55555556
181 30.38674033
182 30.21978022
183 30.60109290
184 30.43478261
185 30.81081081
186 31.18279570
187 31.01604278
188 30.85106383
189 30.68783069
190 30.52631579
191 30.36649215
192 30.20833333
193 30.05181347
194 30.41237113
195 30.76923077
196 31.12244898
197 30.96446701
198 30.80808081
199 30.65326633
200 30.50000000
201 30.84577114
202 30.69306931
203 31.03448276
204 30.88235294
205 31.21951220
206 31.06796117
207 30.91787440
208 30.76923077
209 30.62200957
210 30.47619048
211 30.80568720
212 30.66037736
213 30.51643192
214 30.37383178
215 30.23255814
216 30.09259259
217 29.95391705
218 29.81651376
219 29.68036530
220 29.54545455
221 29.41176471
222 29.72972973
223 29.59641256
224 29.91071429
225 30.22222222
226 30.08849558
227 30.39647577
228 30.70175439
229 30.56768559
230 30.43478261
231 30.30303030
232 30.17241379
233 30.04291845
234 30.34188034
235 30.21276596
236 30.08474576
237 29.95780591
238 29.83193277
239 29.70711297
240 29.58333333
241 29.46058091
242 29.75206612
243 30.04115226
244 29.91803279
245 30.20408163
246 30.08130081
247 29.95951417
248 29.83870968
249 29.71887550
250 29.60000000
251 29.48207171
252 29.36507937
253 29.64426877
254 29.52755906
255 29.80392157
256 29.68750000
257 29.96108949
258 29.84496124
259 30.11583012
260 30.00000000
261 29.88505747
262 29.77099237
263 29.65779468
264 29.92424242
265 30.18867925
266 30.07518797
267 29.96254682
268 29.85074627
269 29.73977695
270 29.62962963
271 29.52029520
272 29.77941176
273 29.67032967
274 29.56204380
275 29.45454545
276 29.71014493
277 29.96389892
278 30.21582734
279 30.10752688
280 30.00000000
281 29.89323843
282 29.78723404
283 29.68197880
284 29.57746479
285 29.47368421
286 29.37062937
287 29.61672474
288 29.51388889
289 29.41176471
290 29.65517241
291 29.89690722
292 30.13698630
293 30.37542662
294 30.61224490
295 30.50847458
296 30.40540541
297 30.30303030
298 30.53691275
299 30.43478261
300 30.66666667
301 30.56478405
302 30.79470199
303 30.69306931
304 30.92105263
305 31.14754098
306 31.04575163
307 31.27035831
308 31.16883117
309 31.06796117
310 30.96774194
311 30.86816720
312 31.08974359
313 31.30990415
314 31.52866242
315 31.42857143
316 31.32911392
317 31.23028391
318 31.13207547
319 31.34796238
320 31.25000000
321 31.15264798
322 31.05590062
323 30.95975232
324 30.86419753
325 31.07692308
326 30.98159509
327 31.19266055
328 31.09756098
329 31.00303951
330 30.90909091
331 30.81570997
332 31.02409639
333 30.93093093
334 30.83832335
335 31.04477612
336 30.95238095
337 30.86053412
338 30.76923077
339 30.67846608
340 30.58823529
341 30.49853372
342 30.40935673
343 30.32069971
344 30.23255814
345 30.14492754
346 30.34682081
347 30.54755043
348 30.45977011
349 30.65902579
350 30.85714286
351 30.76923077
352 30.68181818
353 30.87818697
354 30.79096045
355 30.70422535
356 30.89887640
357 30.81232493
358 30.72625698
359 30.91922006
360 31.11111111
361 31.30193906
362 31.21546961
363 31.40495868
364 31.31868132
365 31.23287671
366 31.14754098
367 31.06267030
368 30.97826087
369 30.89430894
370 31.08108108
371 30.99730458
372 30.91397849
373 30.83109920
374 31.01604278
375 30.93333333
376 30.85106383
377 30.76923077
378 30.68783069
379 30.60686016
380 30.52631579
381 30.70866142
382 30.62827225
383 30.80939948
384 30.72916667
385 30.64935065
386 30.56994819
387 30.49095607
388 30.41237113
389 30.59125964
390 30.51282051
391 30.69053708
392 30.86734694
393 30.78880407
394 30.71065990
395 30.63291139
396 30.80808081
397 30.73047859
398 30.65326633
399 30.82706767
400 30.75000000
401 30.92269327
402 30.84577114
403 30.76923077
404 30.69306931
405 30.61728395
406 30.78817734
407 30.71253071
408 30.63725490
409 30.80684597
410 30.73170732
411 30.65693431
412 30.58252427
413 30.75060533
414 30.91787440
415 31.08433735
416 31.00961538
417 30.93525180
418 30.86124402
419 31.02625298
420 31.19047619
421 31.11638955
422 31.04265403
423 30.96926714
424 31.13207547
425 31.29411765
426 31.22065728
427 31.14754098
428 31.07476636
429 31.23543124
430 31.16279070
431 31.32250580
432 31.48148148
433 31.40877598
434 31.56682028
435 31.49425287
436 31.42201835
437 31.35011442
438 31.50684932
439 31.66287016
440 31.59090909
441 31.51927438
442 31.44796380
443 31.37697517
444 31.30630631
445 31.23595506
446 31.16591928
447 31.09619687
448 31.02678571
449 30.95768374
450 30.88888889
451 30.82039911
452 30.97345133
453 31.12582781
454 31.05726872
455 30.98901099
456 31.14035088
457 31.07221007
458 31.00436681
459 31.15468410
460 31.30434783
461 31.23644252
462 31.16883117
463 31.31749460
464 31.25000000
465 31.18279570
466 31.11587983
467 31.26338330
468 31.19658120
469 31.34328358
470 31.27659574
471 31.21019108
472 31.14406780
473 31.28964059
474 31.22362869
475 31.15789474
476 31.30252101
477 31.23689727
478 31.38075314
479 31.52400835
480 31.45833333
481 31.39293139
482 31.32780083
483 31.26293996
484 31.19834711
485 31.13402062
486 31.06995885
487 31.21149897
488 31.14754098
489 31.08384458
490 31.22448980
491 31.36456212
492 31.30081301
493 31.23732252
494 31.37651822
495 31.51515152
496 31.65322581
497 31.58953722
498 31.52610442
499 31.46292585
500 31.60000000
501 31.53692615
502 31.47410359
503 31.61033797
504 31.54761905
505 31.48514851
506 31.62055336
507 31.55818540
508 31.49606299
509 31.43418468
510 31.56862745
511 31.50684932
512 31.44531250
513 31.38401559
514 31.32295720
515 31.26213592
516 31.20155039
517 31.33462282
518 31.46718147
519 31.40655106
520 31.34615385
521 31.28598848
522 31.41762452
523 31.54875717
524 31.67938931
525 31.61904762
526 31.55893536
527 31.68880455
528 31.62878788
529 31.56899811
530 31.69811321
531 31.63841808
532 31.57894737
533 31.51969981
534 31.46067416
535 31.40186916
536 31.34328358
537 31.47113594
538 31.59851301
539 31.53988868
540 31.48148148
541 31.60813309
542 31.73431734
543 31.86003683
544 31.80147059
545 31.74311927
546 31.68498168
547 31.62705667
548 31.75182482
549 31.69398907
550 31.63636364
551 31.57894737
552 31.70289855
553 31.64556962
554 31.58844765
555 31.53153153
556 31.47482014
557 31.41831239
558 31.54121864
559 31.48479428
560 31.42857143
561 31.37254902
562 31.31672598
563 31.43872114
564 31.38297872
565 31.32743363
566 31.27208481
567 31.21693122
568 31.33802817
569 31.28295255
570 31.22807018
571 31.34851138
572 31.29370629
573 31.23909250
574 31.35888502
575 31.30434783
576 31.42361111
577 31.54246101
578 31.48788927
579 31.43350604
580 31.37931034
581 31.32530120
582 31.27147766
583 31.21783877
584 31.33561644
585 31.28205128
586 31.22866894
587 31.17546848
588 31.12244898
589 31.06960951
590 31.01694915
591 30.96446701
592 30.91216216
593 30.86003373
594 30.97643098
595 30.92436975
596 31.04026846
597 30.98827471
598 30.93645485
599 31.05175292
600 31.00000000
601 31.11480865
602 31.06312292
603 31.17744610
604 31.12582781
605 31.23966942
606 31.18811881
607 31.30148270
608 31.25000000
609 31.19868637
610 31.14754098
611 31.09656301
612 31.04575163
613 30.99510604
614 31.10749186
615 31.05691057
616 31.16883117
617 31.28038898
618 31.22977346
619 31.17932149
620 31.12903226
621 31.07890499
622 31.18971061
623 31.13964687
624 31.08974359
625 31.04000000
626 31.15015974
627 31.10047847
628 31.05095541
629 31.16057234
630 31.11111111
631 31.06180666
632 31.17088608
633 31.12164297
634 31.07255521
635 31.02362205
636 30.97484277
637 30.92621664
638 30.87774295
639 30.82942097
640 30.93750000
641 30.88923557
642 30.99688474
643 30.94867807
644 31.05590062
645 31.00775194
646 30.95975232
647 30.91190108
648 30.86419753
649 30.81664099
650 30.76923077
651 30.72196621
652 30.67484663
653 30.62787136
654 30.73394495
655 30.68702290
656 30.79268293
657 30.74581431
658 30.85106383
659 30.80424886
660 30.75757576
661 30.71104387
662 30.66465257
663 30.61840121
664 30.57228916
665 30.52631579
666 30.48048048
667 30.58470765
668 30.68862275
669 30.64275037
670 30.74626866
671 30.70044709
672 30.65476190
673 30.60921248
674 30.56379822
675 30.51851852
676 30.47337278
677 30.42836041
678 30.38348083
679 30.33873343
680 30.44117647
681 30.54331865
682 30.49853372
683 30.60029283
684 30.55555556
685 30.51094891
686 30.46647230
687 30.42212518
688 30.37790698
689 30.33381713
690 30.28985507
691 30.39073806
692 30.34682081
693 30.30303030
694 30.40345821
695 30.35971223
696 30.45977011
697 30.41606887
698 30.37249284
699 30.47210300
700 30.42857143
701 30.52781740
702 30.62678063
703 30.72546230
704 30.68181818
705 30.63829787
706 30.59490085
707 30.55162659
708 30.50847458
709 30.46544429
710 30.56338028
711 30.66104079
712 30.61797753
713 30.71528752
714 30.81232493
715 30.76923077
716 30.72625698
717 30.68340307
718 30.64066852
719 30.59805285
720 30.55555556
721 30.51317614
722 30.47091413
723 30.56708160
724 30.52486188
725 30.62068966
726 30.71625344
727 30.67400275
728 30.63186813
729 30.72702332
730 30.68493151
731 30.64295486
732 30.73770492
733 30.83219645
734 30.79019074
735 30.74829932
736 30.70652174
737 30.80054274
738 30.75880759
739 30.85250338
740 30.94594595
741 30.90418354
742 30.99730458
743 31.09017497
744 31.18279570
745 31.14093960
746 31.09919571
747 31.05756359
748 31.01604278
749 31.10814419
750 31.20000000
Final result: 31.2000 ±1.6929
Random chance: 25.0000 ±1.5822