icecubesaad commited on
Commit
c19aa30
·
verified ·
1 Parent(s): e17480b

Upload eval_results/base.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. eval_results/base.json +1294 -0
eval_results/base.json ADDED
@@ -0,0 +1,1294 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema": "ladderbench.report/v1",
3
+ "generated_at": "2026-09-27T18:23:54.552461+00:00",
4
+ "ladderbench_version": "0.1.0",
5
+ "model": "base",
6
+ "endpoint": "vllm-offline",
7
+ "probe_set": "all@v1",
8
+ "levels_ordered": [
9
+ "xhigh",
10
+ "medium",
11
+ "low"
12
+ ],
13
+ "summary": {
14
+ "levels": [
15
+ "xhigh",
16
+ "medium",
17
+ "low"
18
+ ],
19
+ "accuracy": [
20
+ 0.8823529411764706,
21
+ 0.8823529411764706,
22
+ 0.8970588235294118
23
+ ],
24
+ "median_thinking_tokens": [
25
+ 65.0,
26
+ 47.5,
27
+ 45.0
28
+ ],
29
+ "spearman_tokens_vs_effort": 0.9999999999999998,
30
+ "spearman_accuracy_vs_effort": -0.8660254037844387,
31
+ "top_level": {
32
+ "level": "xhigh",
33
+ "accuracy": 0.8823529411764706,
34
+ "median_thinking_tokens": 65.0,
35
+ "empty_trace_rate": 0.0
36
+ },
37
+ "token_spread_max_over_min": 1.4444444444444444
38
+ },
39
+ "ladder_integrity": "degraded",
40
+ "findings": [
41
+ "misaligned: accuracy vs effort rho=-0.87"
42
+ ],
43
+ "calibration_delta": null,
44
+ "per_level": {
45
+ "xhigh": {
46
+ "n": 68,
47
+ "accuracy": 0.8824,
48
+ "median_thinking_tokens": 65.0,
49
+ "empty_trace_rate": 0.0,
50
+ "responses": [
51
+ {
52
+ "id": "e01",
53
+ "correct": true,
54
+ "predicted": "43",
55
+ "trace_chars": 121
56
+ },
57
+ {
58
+ "id": "e02",
59
+ "correct": true,
60
+ "predicted": "62",
61
+ "trace_chars": 208
62
+ },
63
+ {
64
+ "id": "e03",
65
+ "correct": true,
66
+ "predicted": "12",
67
+ "trace_chars": 205
68
+ },
69
+ {
70
+ "id": "e04",
71
+ "correct": true,
72
+ "predicted": "12",
73
+ "trace_chars": 110
74
+ },
75
+ {
76
+ "id": "e05",
77
+ "correct": true,
78
+ "predicted": "150",
79
+ "trace_chars": 96
80
+ },
81
+ {
82
+ "id": "e06",
83
+ "correct": true,
84
+ "predicted": "5.75",
85
+ "trace_chars": 154
86
+ },
87
+ {
88
+ "id": "e07",
89
+ "correct": true,
90
+ "predicted": "33",
91
+ "trace_chars": 112
92
+ },
93
+ {
94
+ "id": "e08",
95
+ "correct": true,
96
+ "predicted": "1024",
97
+ "trace_chars": 199
98
+ },
99
+ {
100
+ "id": "e09",
101
+ "correct": true,
102
+ "predicted": "210",
103
+ "trace_chars": 208
104
+ },
105
+ {
106
+ "id": "e10",
107
+ "correct": true,
108
+ "predicted": "495",
109
+ "trace_chars": 205
110
+ },
111
+ {
112
+ "id": "e11",
113
+ "correct": true,
114
+ "predicted": "28",
115
+ "trace_chars": 302
116
+ },
117
+ {
118
+ "id": "e12",
119
+ "correct": true,
120
+ "predicted": "63",
121
+ "trace_chars": 205
122
+ },
123
+ {
124
+ "id": "e13",
125
+ "correct": true,
126
+ "predicted": "64",
127
+ "trace_chars": 247
128
+ },
129
+ {
130
+ "id": "e14",
131
+ "correct": true,
132
+ "predicted": "144",
133
+ "trace_chars": 201
134
+ },
135
+ {
136
+ "id": "e15",
137
+ "correct": true,
138
+ "predicted": "7",
139
+ "trace_chars": 131
140
+ },
141
+ {
142
+ "id": "e16",
143
+ "correct": true,
144
+ "predicted": "8",
145
+ "trace_chars": 86
146
+ },
147
+ {
148
+ "id": "e17",
149
+ "correct": true,
150
+ "predicted": "12",
151
+ "trace_chars": 255
152
+ },
153
+ {
154
+ "id": "e18",
155
+ "correct": true,
156
+ "predicted": "100",
157
+ "trace_chars": 113
158
+ },
159
+ {
160
+ "id": "e19",
161
+ "correct": true,
162
+ "predicted": "90",
163
+ "trace_chars": 227
164
+ },
165
+ {
166
+ "id": "e20",
167
+ "correct": true,
168
+ "predicted": "125",
169
+ "trace_chars": 197
170
+ },
171
+ {
172
+ "id": "m01",
173
+ "correct": true,
174
+ "predicted": "1081",
175
+ "trace_chars": 105
176
+ },
177
+ {
178
+ "id": "m02",
179
+ "correct": true,
180
+ "predicted": "32768",
181
+ "trace_chars": 202
182
+ },
183
+ {
184
+ "id": "m03",
185
+ "correct": true,
186
+ "predicted": "5050",
187
+ "trace_chars": 333
188
+ },
189
+ {
190
+ "id": "m04",
191
+ "correct": true,
192
+ "predicted": "5",
193
+ "trace_chars": 317
194
+ },
195
+ {
196
+ "id": "m05",
197
+ "correct": true,
198
+ "predicted": "36",
199
+ "trace_chars": 453
200
+ },
201
+ {
202
+ "id": "m06",
203
+ "correct": true,
204
+ "predicted": "12",
205
+ "trace_chars": 187
206
+ },
207
+ {
208
+ "id": "m07",
209
+ "correct": true,
210
+ "predicted": "300",
211
+ "trace_chars": 301
212
+ },
213
+ {
214
+ "id": "m08",
215
+ "correct": true,
216
+ "predicted": "204",
217
+ "trace_chars": 432
218
+ },
219
+ {
220
+ "id": "m09",
221
+ "correct": true,
222
+ "predicted": "72",
223
+ "trace_chars": 238
224
+ },
225
+ {
226
+ "id": "m10",
227
+ "correct": true,
228
+ "predicted": "1210",
229
+ "trace_chars": 399
230
+ },
231
+ {
232
+ "id": "m11",
233
+ "correct": true,
234
+ "predicted": "8",
235
+ "trace_chars": 326
236
+ },
237
+ {
238
+ "id": "m12",
239
+ "correct": true,
240
+ "predicted": "28",
241
+ "trace_chars": 341
242
+ },
243
+ {
244
+ "id": "m13",
245
+ "correct": true,
246
+ "predicted": "154",
247
+ "trace_chars": 281
248
+ },
249
+ {
250
+ "id": "m14",
251
+ "correct": true,
252
+ "predicted": "13",
253
+ "trace_chars": 230
254
+ },
255
+ {
256
+ "id": "m15",
257
+ "correct": true,
258
+ "predicted": "75",
259
+ "trace_chars": 263
260
+ },
261
+ {
262
+ "id": "m16",
263
+ "correct": true,
264
+ "predicted": "6",
265
+ "trace_chars": 495
266
+ },
267
+ {
268
+ "id": "m17",
269
+ "correct": true,
270
+ "predicted": "48",
271
+ "trace_chars": 268
272
+ },
273
+ {
274
+ "id": "m18",
275
+ "correct": true,
276
+ "predicted": "18",
277
+ "trace_chars": 371
278
+ },
279
+ {
280
+ "id": "m19",
281
+ "correct": true,
282
+ "predicted": "0.5",
283
+ "trace_chars": 439
284
+ },
285
+ {
286
+ "id": "m20",
287
+ "correct": true,
288
+ "predicted": "216",
289
+ "trace_chars": 158
290
+ },
291
+ {
292
+ "id": "h01",
293
+ "correct": true,
294
+ "predicted": "42",
295
+ "trace_chars": 240
296
+ },
297
+ {
298
+ "id": "h02",
299
+ "correct": true,
300
+ "predicted": "1048576",
301
+ "trace_chars": 253
302
+ },
303
+ {
304
+ "id": "h03",
305
+ "correct": true,
306
+ "predicted": "10",
307
+ "trace_chars": 212
308
+ },
309
+ {
310
+ "id": "h04",
311
+ "correct": true,
312
+ "predicted": "8",
313
+ "trace_chars": 312
314
+ },
315
+ {
316
+ "id": "h05",
317
+ "correct": true,
318
+ "predicted": "100",
319
+ "trace_chars": 271
320
+ },
321
+ {
322
+ "id": "h06",
323
+ "correct": true,
324
+ "predicted": "56",
325
+ "trace_chars": 197
326
+ },
327
+ {
328
+ "id": "h07",
329
+ "correct": true,
330
+ "predicted": "20",
331
+ "trace_chars": 228
332
+ },
333
+ {
334
+ "id": "h08",
335
+ "correct": true,
336
+ "predicted": "10",
337
+ "trace_chars": 147
338
+ },
339
+ {
340
+ "id": "h09",
341
+ "correct": true,
342
+ "predicted": "12",
343
+ "trace_chars": 423
344
+ },
345
+ {
346
+ "id": "h10",
347
+ "correct": true,
348
+ "predicted": "13",
349
+ "trace_chars": 277
350
+ },
351
+ {
352
+ "id": "h11",
353
+ "correct": true,
354
+ "predicted": "17",
355
+ "trace_chars": 165
356
+ },
357
+ {
358
+ "id": "h12",
359
+ "correct": true,
360
+ "predicted": "25",
361
+ "trace_chars": 391
362
+ },
363
+ {
364
+ "id": "h13",
365
+ "correct": true,
366
+ "predicted": "30",
367
+ "trace_chars": 340
368
+ },
369
+ {
370
+ "id": "h14",
371
+ "correct": true,
372
+ "predicted": "132",
373
+ "trace_chars": 180
374
+ },
375
+ {
376
+ "id": "h15",
377
+ "correct": true,
378
+ "predicted": "12",
379
+ "trace_chars": 288
380
+ },
381
+ {
382
+ "id": "h16",
383
+ "correct": true,
384
+ "predicted": "720",
385
+ "trace_chars": 270
386
+ },
387
+ {
388
+ "id": "h17",
389
+ "correct": true,
390
+ "predicted": "1",
391
+ "trace_chars": 328
392
+ },
393
+ {
394
+ "id": "h18",
395
+ "correct": true,
396
+ "predicted": "60",
397
+ "trace_chars": 309
398
+ },
399
+ {
400
+ "id": "h19",
401
+ "correct": true,
402
+ "predicted": "0.375",
403
+ "trace_chars": 463
404
+ },
405
+ {
406
+ "id": "h20",
407
+ "correct": true,
408
+ "predicted": "55",
409
+ "trace_chars": 153
410
+ },
411
+ {
412
+ "id": "i01",
413
+ "correct": false,
414
+ "predicted": null,
415
+ "trace_chars": 1612
416
+ },
417
+ {
418
+ "id": "i02",
419
+ "correct": false,
420
+ "predicted": null,
421
+ "trace_chars": 1188
422
+ },
423
+ {
424
+ "id": "i03",
425
+ "correct": false,
426
+ "predicted": null,
427
+ "trace_chars": 1029
428
+ },
429
+ {
430
+ "id": "i04",
431
+ "correct": false,
432
+ "predicted": null,
433
+ "trace_chars": 2116
434
+ },
435
+ {
436
+ "id": "i05",
437
+ "correct": false,
438
+ "predicted": null,
439
+ "trace_chars": 1407
440
+ },
441
+ {
442
+ "id": "i06",
443
+ "correct": false,
444
+ "predicted": null,
445
+ "trace_chars": 845
446
+ },
447
+ {
448
+ "id": "i07",
449
+ "correct": false,
450
+ "predicted": null,
451
+ "trace_chars": 1645
452
+ },
453
+ {
454
+ "id": "i08",
455
+ "correct": false,
456
+ "predicted": null,
457
+ "trace_chars": 1103
458
+ }
459
+ ]
460
+ },
461
+ "medium": {
462
+ "n": 68,
463
+ "accuracy": 0.8824,
464
+ "median_thinking_tokens": 47.5,
465
+ "empty_trace_rate": 0.0,
466
+ "responses": [
467
+ {
468
+ "id": "e01",
469
+ "correct": true,
470
+ "predicted": "43",
471
+ "trace_chars": 68
472
+ },
473
+ {
474
+ "id": "e02",
475
+ "correct": true,
476
+ "predicted": "62",
477
+ "trace_chars": 159
478
+ },
479
+ {
480
+ "id": "e03",
481
+ "correct": true,
482
+ "predicted": "12",
483
+ "trace_chars": 109
484
+ },
485
+ {
486
+ "id": "e04",
487
+ "correct": true,
488
+ "predicted": "12",
489
+ "trace_chars": 61
490
+ },
491
+ {
492
+ "id": "e05",
493
+ "correct": true,
494
+ "predicted": "150",
495
+ "trace_chars": 88
496
+ },
497
+ {
498
+ "id": "e06",
499
+ "correct": true,
500
+ "predicted": "5.75",
501
+ "trace_chars": 61
502
+ },
503
+ {
504
+ "id": "e07",
505
+ "correct": true,
506
+ "predicted": "33",
507
+ "trace_chars": 108
508
+ },
509
+ {
510
+ "id": "e08",
511
+ "correct": true,
512
+ "predicted": "1024",
513
+ "trace_chars": 192
514
+ },
515
+ {
516
+ "id": "e09",
517
+ "correct": true,
518
+ "predicted": "210",
519
+ "trace_chars": 184
520
+ },
521
+ {
522
+ "id": "e10",
523
+ "correct": true,
524
+ "predicted": "495",
525
+ "trace_chars": 88
526
+ },
527
+ {
528
+ "id": "e11",
529
+ "correct": true,
530
+ "predicted": "28",
531
+ "trace_chars": 182
532
+ },
533
+ {
534
+ "id": "e12",
535
+ "correct": true,
536
+ "predicted": "63",
537
+ "trace_chars": 73
538
+ },
539
+ {
540
+ "id": "e13",
541
+ "correct": true,
542
+ "predicted": "64",
543
+ "trace_chars": 103
544
+ },
545
+ {
546
+ "id": "e14",
547
+ "correct": true,
548
+ "predicted": "144",
549
+ "trace_chars": 76
550
+ },
551
+ {
552
+ "id": "e15",
553
+ "correct": true,
554
+ "predicted": "7",
555
+ "trace_chars": 173
556
+ },
557
+ {
558
+ "id": "e16",
559
+ "correct": true,
560
+ "predicted": "8",
561
+ "trace_chars": 92
562
+ },
563
+ {
564
+ "id": "e17",
565
+ "correct": true,
566
+ "predicted": "12",
567
+ "trace_chars": 161
568
+ },
569
+ {
570
+ "id": "e18",
571
+ "correct": true,
572
+ "predicted": "100",
573
+ "trace_chars": 65
574
+ },
575
+ {
576
+ "id": "e19",
577
+ "correct": true,
578
+ "predicted": "90",
579
+ "trace_chars": 75
580
+ },
581
+ {
582
+ "id": "e20",
583
+ "correct": true,
584
+ "predicted": "125",
585
+ "trace_chars": 74
586
+ },
587
+ {
588
+ "id": "m01",
589
+ "correct": true,
590
+ "predicted": "1081",
591
+ "trace_chars": 158
592
+ },
593
+ {
594
+ "id": "m02",
595
+ "correct": true,
596
+ "predicted": "32768",
597
+ "trace_chars": 225
598
+ },
599
+ {
600
+ "id": "m03",
601
+ "correct": true,
602
+ "predicted": "5050",
603
+ "trace_chars": 176
604
+ },
605
+ {
606
+ "id": "m04",
607
+ "correct": true,
608
+ "predicted": "5",
609
+ "trace_chars": 490
610
+ },
611
+ {
612
+ "id": "m05",
613
+ "correct": true,
614
+ "predicted": "36",
615
+ "trace_chars": 343
616
+ },
617
+ {
618
+ "id": "m06",
619
+ "correct": true,
620
+ "predicted": "12",
621
+ "trace_chars": 236
622
+ },
623
+ {
624
+ "id": "m07",
625
+ "correct": true,
626
+ "predicted": "300",
627
+ "trace_chars": 278
628
+ },
629
+ {
630
+ "id": "m08",
631
+ "correct": true,
632
+ "predicted": "204",
633
+ "trace_chars": 263
634
+ },
635
+ {
636
+ "id": "m09",
637
+ "correct": true,
638
+ "predicted": "72",
639
+ "trace_chars": 294
640
+ },
641
+ {
642
+ "id": "m10",
643
+ "correct": true,
644
+ "predicted": "1210",
645
+ "trace_chars": 220
646
+ },
647
+ {
648
+ "id": "m11",
649
+ "correct": true,
650
+ "predicted": "8",
651
+ "trace_chars": 85
652
+ },
653
+ {
654
+ "id": "m12",
655
+ "correct": true,
656
+ "predicted": "28",
657
+ "trace_chars": 101
658
+ },
659
+ {
660
+ "id": "m13",
661
+ "correct": true,
662
+ "predicted": "154",
663
+ "trace_chars": 211
664
+ },
665
+ {
666
+ "id": "m14",
667
+ "correct": true,
668
+ "predicted": "13",
669
+ "trace_chars": 187
670
+ },
671
+ {
672
+ "id": "m15",
673
+ "correct": true,
674
+ "predicted": "75",
675
+ "trace_chars": 105
676
+ },
677
+ {
678
+ "id": "m16",
679
+ "correct": true,
680
+ "predicted": "6",
681
+ "trace_chars": 283
682
+ },
683
+ {
684
+ "id": "m17",
685
+ "correct": true,
686
+ "predicted": "48",
687
+ "trace_chars": 158
688
+ },
689
+ {
690
+ "id": "m18",
691
+ "correct": true,
692
+ "predicted": "18",
693
+ "trace_chars": 220
694
+ },
695
+ {
696
+ "id": "m19",
697
+ "correct": true,
698
+ "predicted": "0.5",
699
+ "trace_chars": 245
700
+ },
701
+ {
702
+ "id": "m20",
703
+ "correct": true,
704
+ "predicted": "216",
705
+ "trace_chars": 101
706
+ },
707
+ {
708
+ "id": "h01",
709
+ "correct": true,
710
+ "predicted": "42",
711
+ "trace_chars": 261
712
+ },
713
+ {
714
+ "id": "h02",
715
+ "correct": true,
716
+ "predicted": "1048576",
717
+ "trace_chars": 299
718
+ },
719
+ {
720
+ "id": "h03",
721
+ "correct": true,
722
+ "predicted": "10",
723
+ "trace_chars": 174
724
+ },
725
+ {
726
+ "id": "h04",
727
+ "correct": true,
728
+ "predicted": "8",
729
+ "trace_chars": 135
730
+ },
731
+ {
732
+ "id": "h05",
733
+ "correct": true,
734
+ "predicted": "100",
735
+ "trace_chars": 341
736
+ },
737
+ {
738
+ "id": "h06",
739
+ "correct": true,
740
+ "predicted": "56",
741
+ "trace_chars": 197
742
+ },
743
+ {
744
+ "id": "h07",
745
+ "correct": true,
746
+ "predicted": "20",
747
+ "trace_chars": 198
748
+ },
749
+ {
750
+ "id": "h08",
751
+ "correct": true,
752
+ "predicted": "10",
753
+ "trace_chars": 183
754
+ },
755
+ {
756
+ "id": "h09",
757
+ "correct": true,
758
+ "predicted": "12",
759
+ "trace_chars": 208
760
+ },
761
+ {
762
+ "id": "h10",
763
+ "correct": true,
764
+ "predicted": "13",
765
+ "trace_chars": 119
766
+ },
767
+ {
768
+ "id": "h11",
769
+ "correct": true,
770
+ "predicted": "17",
771
+ "trace_chars": 165
772
+ },
773
+ {
774
+ "id": "h12",
775
+ "correct": true,
776
+ "predicted": "25",
777
+ "trace_chars": 176
778
+ },
779
+ {
780
+ "id": "h13",
781
+ "correct": true,
782
+ "predicted": "30",
783
+ "trace_chars": 269
784
+ },
785
+ {
786
+ "id": "h14",
787
+ "correct": true,
788
+ "predicted": "132",
789
+ "trace_chars": 164
790
+ },
791
+ {
792
+ "id": "h15",
793
+ "correct": true,
794
+ "predicted": "12",
795
+ "trace_chars": 447
796
+ },
797
+ {
798
+ "id": "h16",
799
+ "correct": true,
800
+ "predicted": "720",
801
+ "trace_chars": 236
802
+ },
803
+ {
804
+ "id": "h17",
805
+ "correct": true,
806
+ "predicted": "1",
807
+ "trace_chars": 406
808
+ },
809
+ {
810
+ "id": "h18",
811
+ "correct": true,
812
+ "predicted": "60",
813
+ "trace_chars": 372
814
+ },
815
+ {
816
+ "id": "h19",
817
+ "correct": true,
818
+ "predicted": "0.375",
819
+ "trace_chars": 207
820
+ },
821
+ {
822
+ "id": "h20",
823
+ "correct": true,
824
+ "predicted": "55",
825
+ "trace_chars": 196
826
+ },
827
+ {
828
+ "id": "i01",
829
+ "correct": false,
830
+ "predicted": "A",
831
+ "trace_chars": 1800
832
+ },
833
+ {
834
+ "id": "i02",
835
+ "correct": false,
836
+ "predicted": "A",
837
+ "trace_chars": 1113
838
+ },
839
+ {
840
+ "id": "i03",
841
+ "correct": false,
842
+ "predicted": "B",
843
+ "trace_chars": 1240
844
+ },
845
+ {
846
+ "id": "i04",
847
+ "correct": false,
848
+ "predicted": "A",
849
+ "trace_chars": 967
850
+ },
851
+ {
852
+ "id": "i05",
853
+ "correct": false,
854
+ "predicted": "A",
855
+ "trace_chars": 1811
856
+ },
857
+ {
858
+ "id": "i06",
859
+ "correct": false,
860
+ "predicted": "B",
861
+ "trace_chars": 1185
862
+ },
863
+ {
864
+ "id": "i07",
865
+ "correct": false,
866
+ "predicted": "A",
867
+ "trace_chars": 1920
868
+ },
869
+ {
870
+ "id": "i08",
871
+ "correct": false,
872
+ "predicted": "A",
873
+ "trace_chars": 1218
874
+ }
875
+ ]
876
+ },
877
+ "low": {
878
+ "n": 68,
879
+ "accuracy": 0.8971,
880
+ "median_thinking_tokens": 45.0,
881
+ "empty_trace_rate": 0.0,
882
+ "responses": [
883
+ {
884
+ "id": "e01",
885
+ "correct": true,
886
+ "predicted": "43",
887
+ "trace_chars": 51
888
+ },
889
+ {
890
+ "id": "e02",
891
+ "correct": true,
892
+ "predicted": "62",
893
+ "trace_chars": 158
894
+ },
895
+ {
896
+ "id": "e03",
897
+ "correct": true,
898
+ "predicted": "12",
899
+ "trace_chars": 109
900
+ },
901
+ {
902
+ "id": "e04",
903
+ "correct": true,
904
+ "predicted": "12",
905
+ "trace_chars": 61
906
+ },
907
+ {
908
+ "id": "e05",
909
+ "correct": true,
910
+ "predicted": "150",
911
+ "trace_chars": 110
912
+ },
913
+ {
914
+ "id": "e06",
915
+ "correct": true,
916
+ "predicted": "5.75",
917
+ "trace_chars": 61
918
+ },
919
+ {
920
+ "id": "e07",
921
+ "correct": true,
922
+ "predicted": "33",
923
+ "trace_chars": 58
924
+ },
925
+ {
926
+ "id": "e08",
927
+ "correct": true,
928
+ "predicted": "1024",
929
+ "trace_chars": 192
930
+ },
931
+ {
932
+ "id": "e09",
933
+ "correct": true,
934
+ "predicted": "210",
935
+ "trace_chars": 170
936
+ },
937
+ {
938
+ "id": "e10",
939
+ "correct": true,
940
+ "predicted": "495",
941
+ "trace_chars": 88
942
+ },
943
+ {
944
+ "id": "e11",
945
+ "correct": true,
946
+ "predicted": "28",
947
+ "trace_chars": 130
948
+ },
949
+ {
950
+ "id": "e12",
951
+ "correct": true,
952
+ "predicted": "63",
953
+ "trace_chars": 73
954
+ },
955
+ {
956
+ "id": "e13",
957
+ "correct": true,
958
+ "predicted": "64",
959
+ "trace_chars": 80
960
+ },
961
+ {
962
+ "id": "e14",
963
+ "correct": true,
964
+ "predicted": "144",
965
+ "trace_chars": 58
966
+ },
967
+ {
968
+ "id": "e15",
969
+ "correct": true,
970
+ "predicted": "7",
971
+ "trace_chars": 139
972
+ },
973
+ {
974
+ "id": "e16",
975
+ "correct": true,
976
+ "predicted": "8",
977
+ "trace_chars": 84
978
+ },
979
+ {
980
+ "id": "e17",
981
+ "correct": true,
982
+ "predicted": "12",
983
+ "trace_chars": 173
984
+ },
985
+ {
986
+ "id": "e18",
987
+ "correct": true,
988
+ "predicted": "100",
989
+ "trace_chars": 65
990
+ },
991
+ {
992
+ "id": "e19",
993
+ "correct": true,
994
+ "predicted": "90",
995
+ "trace_chars": 73
996
+ },
997
+ {
998
+ "id": "e20",
999
+ "correct": true,
1000
+ "predicted": "125",
1001
+ "trace_chars": 74
1002
+ },
1003
+ {
1004
+ "id": "m01",
1005
+ "correct": true,
1006
+ "predicted": "1081",
1007
+ "trace_chars": 91
1008
+ },
1009
+ {
1010
+ "id": "m02",
1011
+ "correct": true,
1012
+ "predicted": "32768",
1013
+ "trace_chars": 235
1014
+ },
1015
+ {
1016
+ "id": "m03",
1017
+ "correct": true,
1018
+ "predicted": "5050",
1019
+ "trace_chars": 216
1020
+ },
1021
+ {
1022
+ "id": "m04",
1023
+ "correct": true,
1024
+ "predicted": "5",
1025
+ "trace_chars": 528
1026
+ },
1027
+ {
1028
+ "id": "m05",
1029
+ "correct": true,
1030
+ "predicted": "36",
1031
+ "trace_chars": 280
1032
+ },
1033
+ {
1034
+ "id": "m06",
1035
+ "correct": true,
1036
+ "predicted": "12",
1037
+ "trace_chars": 221
1038
+ },
1039
+ {
1040
+ "id": "m07",
1041
+ "correct": true,
1042
+ "predicted": "300",
1043
+ "trace_chars": 241
1044
+ },
1045
+ {
1046
+ "id": "m08",
1047
+ "correct": true,
1048
+ "predicted": "204",
1049
+ "trace_chars": 246
1050
+ },
1051
+ {
1052
+ "id": "m09",
1053
+ "correct": true,
1054
+ "predicted": "72",
1055
+ "trace_chars": 198
1056
+ },
1057
+ {
1058
+ "id": "m10",
1059
+ "correct": true,
1060
+ "predicted": "1210",
1061
+ "trace_chars": 200
1062
+ },
1063
+ {
1064
+ "id": "m11",
1065
+ "correct": true,
1066
+ "predicted": "8",
1067
+ "trace_chars": 155
1068
+ },
1069
+ {
1070
+ "id": "m12",
1071
+ "correct": true,
1072
+ "predicted": "28",
1073
+ "trace_chars": 152
1074
+ },
1075
+ {
1076
+ "id": "m13",
1077
+ "correct": true,
1078
+ "predicted": "154",
1079
+ "trace_chars": 144
1080
+ },
1081
+ {
1082
+ "id": "m14",
1083
+ "correct": true,
1084
+ "predicted": "13",
1085
+ "trace_chars": 162
1086
+ },
1087
+ {
1088
+ "id": "m15",
1089
+ "correct": true,
1090
+ "predicted": "75",
1091
+ "trace_chars": 90
1092
+ },
1093
+ {
1094
+ "id": "m16",
1095
+ "correct": true,
1096
+ "predicted": "6",
1097
+ "trace_chars": 180
1098
+ },
1099
+ {
1100
+ "id": "m17",
1101
+ "correct": true,
1102
+ "predicted": "48",
1103
+ "trace_chars": 160
1104
+ },
1105
+ {
1106
+ "id": "m18",
1107
+ "correct": true,
1108
+ "predicted": "18",
1109
+ "trace_chars": 220
1110
+ },
1111
+ {
1112
+ "id": "m19",
1113
+ "correct": true,
1114
+ "predicted": "0.5",
1115
+ "trace_chars": 123
1116
+ },
1117
+ {
1118
+ "id": "m20",
1119
+ "correct": true,
1120
+ "predicted": "216",
1121
+ "trace_chars": 69
1122
+ },
1123
+ {
1124
+ "id": "h01",
1125
+ "correct": true,
1126
+ "predicted": "42",
1127
+ "trace_chars": 252
1128
+ },
1129
+ {
1130
+ "id": "h02",
1131
+ "correct": true,
1132
+ "predicted": "1048576",
1133
+ "trace_chars": 299
1134
+ },
1135
+ {
1136
+ "id": "h03",
1137
+ "correct": true,
1138
+ "predicted": "10",
1139
+ "trace_chars": 121
1140
+ },
1141
+ {
1142
+ "id": "h04",
1143
+ "correct": true,
1144
+ "predicted": "8",
1145
+ "trace_chars": 570
1146
+ },
1147
+ {
1148
+ "id": "h05",
1149
+ "correct": true,
1150
+ "predicted": "100",
1151
+ "trace_chars": 275
1152
+ },
1153
+ {
1154
+ "id": "h06",
1155
+ "correct": true,
1156
+ "predicted": "56",
1157
+ "trace_chars": 196
1158
+ },
1159
+ {
1160
+ "id": "h07",
1161
+ "correct": true,
1162
+ "predicted": "20",
1163
+ "trace_chars": 179
1164
+ },
1165
+ {
1166
+ "id": "h08",
1167
+ "correct": true,
1168
+ "predicted": "10",
1169
+ "trace_chars": 187
1170
+ },
1171
+ {
1172
+ "id": "h09",
1173
+ "correct": true,
1174
+ "predicted": "12",
1175
+ "trace_chars": 206
1176
+ },
1177
+ {
1178
+ "id": "h10",
1179
+ "correct": true,
1180
+ "predicted": "13",
1181
+ "trace_chars": 138
1182
+ },
1183
+ {
1184
+ "id": "h11",
1185
+ "correct": true,
1186
+ "predicted": "17",
1187
+ "trace_chars": 156
1188
+ },
1189
+ {
1190
+ "id": "h12",
1191
+ "correct": true,
1192
+ "predicted": "25",
1193
+ "trace_chars": 157
1194
+ },
1195
+ {
1196
+ "id": "h13",
1197
+ "correct": true,
1198
+ "predicted": "30",
1199
+ "trace_chars": 304
1200
+ },
1201
+ {
1202
+ "id": "h14",
1203
+ "correct": true,
1204
+ "predicted": "132",
1205
+ "trace_chars": 161
1206
+ },
1207
+ {
1208
+ "id": "h15",
1209
+ "correct": true,
1210
+ "predicted": "12",
1211
+ "trace_chars": 404
1212
+ },
1213
+ {
1214
+ "id": "h16",
1215
+ "correct": true,
1216
+ "predicted": "720",
1217
+ "trace_chars": 216
1218
+ },
1219
+ {
1220
+ "id": "h17",
1221
+ "correct": true,
1222
+ "predicted": "1",
1223
+ "trace_chars": 267
1224
+ },
1225
+ {
1226
+ "id": "h18",
1227
+ "correct": true,
1228
+ "predicted": "60",
1229
+ "trace_chars": 464
1230
+ },
1231
+ {
1232
+ "id": "h19",
1233
+ "correct": true,
1234
+ "predicted": "0.375",
1235
+ "trace_chars": 288
1236
+ },
1237
+ {
1238
+ "id": "h20",
1239
+ "correct": true,
1240
+ "predicted": "55",
1241
+ "trace_chars": 196
1242
+ },
1243
+ {
1244
+ "id": "i01",
1245
+ "correct": false,
1246
+ "predicted": "A",
1247
+ "trace_chars": 1874
1248
+ },
1249
+ {
1250
+ "id": "i02",
1251
+ "correct": false,
1252
+ "predicted": "A",
1253
+ "trace_chars": 941
1254
+ },
1255
+ {
1256
+ "id": "i03",
1257
+ "correct": false,
1258
+ "predicted": "B",
1259
+ "trace_chars": 937
1260
+ },
1261
+ {
1262
+ "id": "i04",
1263
+ "correct": false,
1264
+ "predicted": "A",
1265
+ "trace_chars": 917
1266
+ },
1267
+ {
1268
+ "id": "i05",
1269
+ "correct": false,
1270
+ "predicted": "A",
1271
+ "trace_chars": 1370
1272
+ },
1273
+ {
1274
+ "id": "i06",
1275
+ "correct": true,
1276
+ "predicted": "A",
1277
+ "trace_chars": 1034
1278
+ },
1279
+ {
1280
+ "id": "i07",
1281
+ "correct": false,
1282
+ "predicted": "B",
1283
+ "trace_chars": 1691
1284
+ },
1285
+ {
1286
+ "id": "i08",
1287
+ "correct": false,
1288
+ "predicted": "A",
1289
+ "trace_chars": 1221
1290
+ }
1291
+ ]
1292
+ }
1293
+ }
1294
+ }