DeepSeek-R1-Distill-Qwen-7B-GGUF / scores /deepseek-r1-distill-qwen-7b-iq3_m.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 40.00000000
16 43.75000000
17 41.17647059
18 38.88888889
19 42.10526316
20 40.00000000
21 38.09523810
22 36.36363636
23 34.78260870
24 33.33333333
25 36.00000000
26 34.61538462
27 33.33333333
28 35.71428571
29 37.93103448
30 40.00000000
31 41.93548387
32 43.75000000
33 42.42424242
34 41.17647059
35 42.85714286
36 41.66666667
37 40.54054054
38 42.10526316
39 41.02564103
40 40.00000000
41 41.46341463
42 40.47619048
43 39.53488372
44 38.63636364
45 37.77777778
46 36.95652174
47 36.17021277
48 37.50000000
49 38.77551020
50 40.00000000
51 39.21568627
52 38.46153846
53 37.73584906
54 37.03703704
55 38.18181818
56 39.28571429
57 38.59649123
58 37.93103448
59 37.28813559
60 36.66666667
61 36.06557377
62 35.48387097
63 34.92063492
64 34.37500000
65 33.84615385
66 33.33333333
67 32.83582090
68 32.35294118
69 33.33333333
70 34.28571429
71 33.80281690
72 34.72222222
73 34.24657534
74 33.78378378
75 34.66666667
76 35.52631579
77 36.36363636
78 37.17948718
79 36.70886076
80 37.50000000
81 37.03703704
82 36.58536585
83 37.34939759
84 38.09523810
85 37.64705882
86 37.20930233
87 37.93103448
88 38.63636364
89 38.20224719
90 37.77777778
91 37.36263736
92 36.95652174
93 36.55913978
94 36.17021277
95 35.78947368
96 36.45833333
97 36.08247423
98 35.71428571
99 35.35353535
100 35.00000000
101 34.65346535
102 34.31372549
103 33.98058252
104 33.65384615
105 33.33333333
106 33.01886792
107 32.71028037
108 33.33333333
109 33.02752294
110 32.72727273
111 32.43243243
112 32.14285714
113 32.74336283
114 33.33333333
115 33.91304348
116 33.62068966
117 33.33333333
118 33.05084746
119 32.77310924
120 32.50000000
121 32.23140496
122 31.96721311
123 31.70731707
124 31.45161290
125 32.00000000
126 31.74603175
127 31.49606299
128 31.25000000
129 31.00775194
130 30.76923077
131 31.29770992
132 31.06060606
133 30.82706767
134 30.59701493
135 30.37037037
136 30.88235294
137 30.65693431
138 30.43478261
139 30.21582734
140 30.00000000
141 29.78723404
142 29.57746479
143 30.06993007
144 30.55555556
145 30.34482759
146 30.13698630
147 29.93197279
148 30.40540541
149 30.20134228
150 30.00000000
151 29.80132450
152 30.26315789
153 30.06535948
154 29.87012987
155 29.67741935
156 29.48717949
157 29.93630573
158 30.37974684
159 30.18867925
160 30.62500000
161 30.43478261
162 30.24691358
163 30.06134969
164 29.87804878
165 30.30303030
166 30.12048193
167 30.53892216
168 30.35714286
169 30.17751479
170 30.00000000
171 29.82456140
172 29.65116279
173 29.47976879
174 29.31034483
175 29.14285714
176 29.54545455
177 29.37853107
178 29.21348315
179 29.60893855
180 30.00000000
181 29.83425414
182 29.67032967
183 30.05464481
184 29.89130435
185 30.27027027
186 30.64516129
187 30.48128342
188 30.31914894
189 30.15873016
190 30.00000000
191 29.84293194
192 29.68750000
193 29.53367876
194 29.89690722
195 30.25641026
196 30.61224490
197 30.45685279
198 30.30303030
199 30.15075377
200 30.00000000
201 30.34825871
202 30.19801980
203 30.54187192
204 30.39215686
205 30.73170732
206 30.58252427
207 30.43478261
208 30.28846154
209 30.14354067
210 30.00000000
211 30.33175355
212 30.18867925
213 30.04694836
214 29.90654206
215 29.76744186
216 29.62962963
217 29.49308756
218 29.35779817
219 29.22374429
220 29.09090909
221 28.95927602
222 29.27927928
223 29.14798206
224 29.01785714
225 29.33333333
226 29.20353982
227 29.51541850
228 29.82456140
229 29.69432314
230 29.56521739
231 29.43722944
232 29.31034483
233 29.18454936
234 29.48717949
235 29.36170213
236 29.23728814
237 29.11392405
238 28.99159664
239 28.87029289
240 28.75000000
241 28.63070539
242 28.92561983
243 29.21810700
244 29.09836066
245 29.38775510
246 29.26829268
247 29.14979757
248 29.03225806
249 28.91566265
250 28.80000000
251 28.68525896
252 28.57142857
253 28.85375494
254 28.74015748
255 29.01960784
256 28.90625000
257 29.18287938
258 29.06976744
259 29.34362934
260 29.23076923
261 29.11877395
262 29.00763359
263 28.89733840
264 29.16666667
265 29.05660377
266 28.94736842
267 28.83895131
268 28.73134328
269 28.62453532
270 28.51851852
271 28.41328413
272 28.67647059
273 28.57142857
274 28.46715328
275 28.36363636
276 28.62318841
277 28.88086643
278 28.77697842
279 28.67383513
280 28.57142857
281 28.46975089
282 28.36879433
283 28.26855124
284 28.16901408
285 28.07017544
286 27.97202797
287 28.22299652
288 28.12500000
289 28.02768166
290 28.27586207
291 28.52233677
292 28.76712329
293 29.01023891
294 29.25170068
295 29.15254237
296 29.05405405
297 28.95622896
298 29.19463087
299 29.09698997
300 29.33333333
301 29.23588040
302 29.47019868
303 29.37293729
304 29.60526316
305 29.83606557
306 29.73856209
307 29.64169381
308 29.54545455
309 29.44983819
310 29.35483871
311 29.26045016
312 29.48717949
313 29.71246006
314 29.93630573
315 29.84126984
316 29.74683544
317 29.65299685
318 29.55974843
319 29.78056426
320 29.68750000
321 29.59501558
322 29.50310559
323 29.41176471
324 29.32098765
325 29.53846154
326 29.44785276
327 29.66360856
328 29.87804878
329 29.78723404
330 29.69696970
331 29.60725076
332 29.81927711
333 29.72972973
334 29.64071856
335 29.85074627
336 29.76190476
337 29.67359050
338 29.58579882
339 29.49852507
340 29.41176471
341 29.32551320
342 29.23976608
343 29.15451895
344 29.06976744
345 28.98550725
346 29.19075145
347 29.39481268
348 29.31034483
349 29.51289398
350 29.71428571
351 29.62962963
352 29.54545455
353 29.74504249
354 29.66101695
355 29.57746479
356 29.77528090
357 29.69187675
358 29.60893855
359 29.52646240
360 29.72222222
361 29.91689751
362 29.83425414
363 30.02754821
364 29.94505495
365 29.86301370
366 29.78142077
367 29.70027248
368 29.61956522
369 29.53929539
370 29.72972973
371 29.64959569
372 29.56989247
373 29.49061662
374 29.41176471
375 29.60000000
376 29.52127660
377 29.44297082
378 29.36507937
379 29.28759894
380 29.21052632
381 29.13385827
382 29.05759162
383 29.24281984
384 29.16666667
385 29.09090909
386 29.01554404
387 28.94056848
388 28.86597938
389 29.04884319
390 28.97435897
391 29.15601023
392 29.33673469
393 29.26208651
394 29.18781726
395 29.11392405
396 29.29292929
397 29.21914358
398 29.14572864
399 29.32330827
400 29.25000000
401 29.42643392
402 29.35323383
403 29.28039702
404 29.20792079
405 29.13580247
406 29.06403941
407 28.99262899
408 28.92156863
409 29.09535452
410 29.02439024
411 28.95377129
412 28.88349515
413 29.05569007
414 29.22705314
415 29.39759036
416 29.32692308
417 29.25659472
418 29.18660287
419 29.35560859
420 29.52380952
421 29.45368171
422 29.38388626
423 29.31442080
424 29.48113208
425 29.64705882
426 29.57746479
427 29.50819672
428 29.67289720
429 29.83682984
430 29.76744186
431 29.93039443
432 30.09259259
433 30.02309469
434 30.18433180
435 30.11494253
436 30.04587156
437 29.97711670
438 30.13698630
439 30.29612756
440 30.22727273
441 30.15873016
442 30.09049774
443 30.02257336
444 29.95495495
445 29.88764045
446 29.82062780
447 29.75391499
448 29.68750000
449 29.62138085
450 29.55555556
451 29.49002217
452 29.64601770
453 29.80132450
454 29.73568282
455 29.67032967
456 29.82456140
457 29.75929978
458 29.69432314
459 29.84749455
460 30.00000000
461 29.93492408
462 29.87012987
463 30.02159827
464 29.95689655
465 29.89247312
466 29.82832618
467 29.97858672
468 29.91452991
469 30.06396588
470 30.00000000
471 29.93630573
472 29.87288136
473 30.02114165
474 29.95780591
475 29.89473684
476 30.04201681
477 29.97903564
478 30.12552301
479 30.27139875
480 30.20833333
481 30.14553015
482 30.08298755
483 30.02070393
484 29.95867769
485 29.89690722
486 29.83539095
487 29.97946612
488 29.91803279
489 29.85685072
490 30.00000000
491 30.14256619
492 30.08130081
493 30.02028398
494 30.16194332
495 30.30303030
496 30.44354839
497 30.38229376
498 30.32128514
499 30.26052104
500 30.40000000
501 30.33932136
502 30.27888446
503 30.21868787
504 30.35714286
505 30.29702970
506 30.43478261
507 30.37475345
508 30.31496063
509 30.25540275
510 30.39215686
511 30.33268102
512 30.27343750
513 30.21442495
514 30.15564202
515 30.09708738
516 30.03875969
517 30.17408124
518 30.30888031
519 30.25048170
520 30.19230769
521 30.13435701
522 30.26819923
523 30.40152964
524 30.53435115
525 30.47619048
526 30.41825095
527 30.55028463
528 30.49242424
529 30.62381853
530 30.75471698
531 30.69679849
532 30.63909774
533 30.58161351
534 30.52434457
535 30.65420561
536 30.59701493
537 30.72625698
538 30.85501859
539 30.79777365
540 30.74074074
541 30.86876155
542 30.99630996
543 30.93922652
544 30.88235294
545 30.82568807
546 30.76923077
547 30.71297989
548 30.83941606
549 30.78324226
550 30.72727273
551 30.67150635
552 30.79710145
553 30.74141049
554 30.68592058
555 30.63063063
556 30.57553957
557 30.52064632
558 30.64516129
559 30.59033989
560 30.53571429
561 30.48128342
562 30.42704626
563 30.55062167
564 30.49645390
565 30.44247788
566 30.38869258
567 30.33509700
568 30.45774648
569 30.40421793
570 30.35087719
571 30.47285464
572 30.41958042
573 30.36649215
574 30.48780488
575 30.43478261
576 30.55555556
577 30.67590988
578 30.62283737
579 30.56994819
580 30.51724138
581 30.46471601
582 30.41237113
583 30.36020583
584 30.47945205
585 30.42735043
586 30.37542662
587 30.32367973
588 30.27210884
589 30.22071307
590 30.16949153
591 30.11844332
592 30.06756757
593 30.01686341
594 30.13468013
595 30.08403361
596 30.20134228
597 30.15075377
598 30.10033445
599 30.21702838
600 30.16666667
601 30.28286190
602 30.23255814
603 30.34825871
604 30.29801325
605 30.41322314
606 30.36303630
607 30.47775947
608 30.42763158
609 30.37766831
610 30.32786885
611 30.27823241
612 30.22875817
613 30.17944535
614 30.29315961
615 30.24390244
616 30.35714286
617 30.47001621
618 30.42071197
619 30.37156704
620 30.32258065
621 30.27375201
622 30.38585209
623 30.33707865
624 30.28846154
625 30.24000000
626 30.35143770
627 30.30303030
628 30.41401274
629 30.52464229
630 30.47619048
631 30.42789223
632 30.53797468
633 30.48973144
634 30.44164038
635 30.39370079
636 30.34591195
637 30.29827316
638 30.25078370
639 30.35993740
640 30.46875000
641 30.42121685
642 30.52959502
643 30.48211509
644 30.59006211
645 30.54263566
646 30.49535604
647 30.44822257
648 30.40123457
649 30.35439137
650 30.30769231
651 30.26113671
652 30.21472393
653 30.16845329
654 30.27522936
655 30.22900763
656 30.33536585
657 30.28919330
658 30.39513678
659 30.34901366
660 30.30303030
661 30.25718608
662 30.21148036
663 30.16591252
664 30.12048193
665 30.07518797
666 30.03003003
667 29.98500750
668 30.08982036
669 30.04484305
670 30.14925373
671 30.10432191
672 30.05952381
673 30.01485884
674 29.97032641
675 29.92592593
676 29.88165680
677 29.83751846
678 29.79351032
679 29.74963181
680 29.85294118
681 29.95594714
682 29.91202346
683 30.01464129
684 29.97076023
685 29.92700730
686 29.88338192
687 29.83988355
688 29.79651163
689 29.75326560
690 29.71014493
691 29.81186686
692 29.76878613
693 29.72582973
694 29.68299712
695 29.64028777
696 29.74137931
697 29.69870875
698 29.65616046
699 29.75679542
700 29.71428571
701 29.81455064
702 29.91452991
703 30.01422475
704 29.97159091
705 29.92907801
706 29.88668555
707 29.84441301
708 29.80225989
709 29.76022567
710 29.85915493
711 29.95780591
712 29.91573034
713 30.01402525
714 30.11204482
715 30.06993007
716 30.02793296
717 29.98605300
718 29.94428969
719 29.90264256
720 29.86111111
721 29.81969487
722 29.77839335
723 29.87551867
724 29.83425414
725 29.93103448
726 30.02754821
727 29.98624484
728 29.94505495
729 30.04115226
730 30.00000000
731 29.95896033
732 30.05464481
733 30.01364256
734 29.97275204
735 29.93197279
736 30.02717391
737 30.12211669
738 30.08130081
739 30.17591340
740 30.27027027
741 30.22941970
742 30.32345013
743 30.41722746
744 30.51075269
745 30.46979866
746 30.42895442
747 30.38821954
748 30.34759358
749 30.30707610
750 30.40000000
Final result: 30.4000 ±1.6807
Random chance: 25.0000 ±1.5822