X-ai / grok-4.3
max
96.6%
197 / 204 fixtures · 1 run(s)
70,161 input / 101,227 total output / 98,145 reasoning within output tokens $0.30327115
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1%
Text: 96.6% →
JSON: 95.6%
+3
Gained
JSON pass / text fail
−5
Lost
Text pass / JSON fail
192
Unchanged Pass
Both pass
4
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| rebase | 91.7% | 83.3% | -8.3% |
| git_show | 91.7% | 100% | + 8.3% |
| merge_conflicts | 75% | 83.3% | + 8.3% |
| blame_forensics | 100% | 100% | + 0% |
| cherry_pick | 91.7% | 91.7% | + 0% |
| commit_messages | 100% | 100% | + 0% |
| commit_squash | 100% | 100% | + 0% |
| git_bisect | 100% | 100% | + 0% |
| git_clean | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 91.7% | 91.7% | + 0% |
| tag_management | 100% | 100% | + 0% |
| worktree_usage | 100% | 100% | + 0% |
Changed Fixtures (8)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
391
Input
531
Total output
527
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
379
Input
634
Total output
630
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
398
Input
733
Total output
727
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
349
Input
456
Total output
451
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
406
Input
1,036
Total output
1,033
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
384
Input
729
Total output
726
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
360
Input
458
Total output
454
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
383
Input
569
Total output
566
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
352
Input
466
Total output
463
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
534
Input
905
Total output
902
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
381
Input
548
Total output
545
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
307
Input
494
Total output
490
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
269
Input
578
Total output
575
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
286
Input
512
Total output
507
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
267
Input
398
Total output
397
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
304
Input
453
Total output
448
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
281
Input
446
Total output
443
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
297
Input
314
Total output
307
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
274
Input
175
Total output
170
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
291
Input
176
Total output
167
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
256
Input
312
Total output
311
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
286
Input
326
Total output
321
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
246
Input
165
Total output
164
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
326
Input
360
Total output
350
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
269
Input
985
Total output
981
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
289
Input
2,474
Total output
2,467
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
259
Input
761
Total output
758
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
316
Input
1,235
Total output
1,211
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
319
Input
340
Total output
320
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
304
Input
506
Total output
482
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
298
Input
244
Total output
236
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
298
Input
185
Total output
179
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
279
Input
147
Total output
142
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
380
Input
466
Total output
442
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
337
Input
423
Total output
402
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
427
Input
2,328
Total output
2,291
Reasoning within output
commit_messages f001
89.3%
Passed
Tokens
276
Input
439
Total output
431
Reasoning within output
commit_messages f002
84.7%
Passed
Tokens
371
Input
548
Total output
539
Reasoning within output
commit_messages f003
91.7%
Passed
Tokens
258
Input
382
Total output
374
Reasoning within output
commit_messages f004
93%
Passed
Tokens
283
Input
203
Total output
200
Reasoning within output
commit_messages f005
89.7%
Passed
Tokens
274
Input
353
Total output
348
Reasoning within output
commit_messages f006
93.3%
Passed
Tokens
307
Input
356
Total output
350
Reasoning within output
commit_messages f007
90%
Passed
Tokens
344
Input
421
Total output
413
Reasoning within output
commit_messages f008
91.7%
Passed
Tokens
247
Input
519
Total output
515
Reasoning within output
commit_messages f009
86.7%
Passed
Tokens
298
Input
518
Total output
510
Reasoning within output
commit_messages f010
91.7%
Passed
Tokens
431
Input
355
Total output
349
Reasoning within output
commit_messages f011
79.3%
Passed
Tokens
316
Input
458
Total output
445
Reasoning within output
commit_messages f012
93.3%
Passed
Tokens
295
Input
406
Total output
401
Reasoning within output
commit_squash f001
100%
Passed
Tokens
306
Input
1,037
Total output
1,025
Reasoning within output
commit_squash f002
100%
Passed
Tokens
291
Input
437
Total output
429
Reasoning within output
commit_squash f003
100%
Passed
Tokens
296
Input
376
Total output
364
Reasoning within output
commit_squash f004
100%
Passed
Tokens
288
Input
337
Total output
326
Reasoning within output
commit_squash f005
100%
Passed
Tokens
287
Input
324
Total output
317
Reasoning within output
commit_squash f006
100%
Passed
Tokens
269
Input
478
Total output
467
Reasoning within output
commit_squash f007
100%
Passed
Tokens
271
Input
321
Total output
309
Reasoning within output
commit_squash f008
100%
Passed
Tokens
284
Input
299
Total output
287
Reasoning within output
commit_squash f009
100%
Passed
Tokens
276
Input
362
Total output
351
Reasoning within output
commit_squash f010
100%
Passed
Tokens
293
Input
391
Total output
376
Reasoning within output
commit_squash f011
100%
Passed
Tokens
297
Input
247
Total output
232
Reasoning within output
commit_squash f012
100%
Passed
Tokens
296
Input
223
Total output
203
Reasoning within output
git_bisect f001
100%
Passed
Tokens
351
Input
350
Total output
346
Reasoning within output
git_bisect f002
100%
Passed
Tokens
364
Input
456
Total output
453
Reasoning within output
git_bisect f003
100%
Passed
Tokens
368
Input
640
Total output
565
Reasoning within output
git_bisect f004
100%
Passed
Tokens
370
Input
495
Total output
492
Reasoning within output
git_bisect f005
100%
Passed
Tokens
366
Input
739
Total output
735
Reasoning within output
git_bisect f006
100%
Passed
Tokens
391
Input
463
Total output
460
Reasoning within output
git_bisect f007
100%
Passed
Tokens
370
Input
406
Total output
359
Reasoning within output
git_bisect f008
100%
Passed
Tokens
372
Input
432
Total output
429
Reasoning within output
git_bisect f009
100%
Passed
Tokens
366
Input
333
Total output
327
Reasoning within output
git_bisect f010
100%
Passed
Tokens
368
Input
443
Total output
439
Reasoning within output
git_bisect f011
100%
Passed
Tokens
368
Input
648
Total output
644
Reasoning within output
git_bisect f012
100%
Passed
Tokens
395
Input
361
Total output
356
Reasoning within output
git_clean f001
100%
Passed
Tokens
225
Input
359
Total output
347
Reasoning within output
git_clean f002
100%
Passed
Tokens
236
Input
210
Total output
206
Reasoning within output
git_clean f003
100%
Passed
Tokens
233
Input
102
Total output
98
Reasoning within output
git_clean f004
100%
Passed
Tokens
233
Input
668
Total output
658
Reasoning within output
git_clean f005
100%
Passed
Tokens
225
Input
451
Total output
445
Reasoning within output
git_clean f006
100%
Passed
Tokens
248
Input
280
Total output
274
Reasoning within output
git_clean f007
100%
Passed
Tokens
240
Input
774
Total output
766
Reasoning within output
git_clean f008
100%
Passed
Tokens
247
Input
354
Total output
350
Reasoning within output
git_clean f009
100%
Passed
Tokens
240
Input
558
Total output
552
Reasoning within output
git_clean f010
100%
Passed
Tokens
237
Input
213
Total output
204
Reasoning within output
git_clean f011
100%
Passed
Tokens
237
Input
367
Total output
357
Reasoning within output
git_clean f012
100%
Passed
Tokens
239
Input
567
Total output
560
Reasoning within output
git_grep f001
100%
Passed
Tokens
229
Input
98
Total output
95
Reasoning within output
git_grep f002
100%
Passed
Tokens
239
Input
380
Total output
379
Reasoning within output
git_grep f003
100%
Passed
Tokens
264
Input
219
Total output
218
Reasoning within output
git_grep f004
100%
Passed
Tokens
253
Input
159
Total output
154
Reasoning within output
git_grep f005
100%
Passed
Tokens
282
Input
355
Total output
354
Reasoning within output
git_grep f006
100%
Passed
Tokens
218
Input
146
Total output
145
Reasoning within output
git_grep f007
100%
Passed
Tokens
333
Input
1,858
Total output
1,857
Reasoning within output
git_grep f008
100%
Passed
Tokens
237
Input
183
Total output
182
Reasoning within output
git_grep f009
100%
Passed
Tokens
231
Input
104
Total output
101
Reasoning within output
git_grep f010
100%
Passed
Tokens
240
Input
449
Total output
448
Reasoning within output
git_grep f011
100%
Passed
Tokens
285
Input
236
Total output
235
Reasoning within output
git_grep f012
100%
Passed
Tokens
242
Input
147
Total output
139
Reasoning within output
git_log_format f001
100%
Passed
Tokens
862
Input
242
Total output
241
Reasoning within output
git_log_format f002
100%
Passed
Tokens
868
Input
249
Total output
242
Reasoning within output
git_log_format f003
100%
Passed
Tokens
733
Input
435
Total output
426
Reasoning within output
git_log_format f004
100%
Passed
Tokens
849
Input
238
Total output
237
Reasoning within output
git_log_format f005
100%
Passed
Tokens
739
Input
276
Total output
271
Reasoning within output
git_log_format f006
100%
Passed
Tokens
865
Input
351
Total output
350
Reasoning within output
git_log_format f007
100%
Passed
Tokens
886
Input
193
Total output
189
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,125
Input
164
Total output
163
Reasoning within output
git_log_format f009
100%
Passed
Tokens
737
Input
131
Total output
130
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,212
Input
296
Total output
295
Reasoning within output
git_log_format f011
100%
Passed
Tokens
510
Input
200
Total output
198
Reasoning within output
git_log_format f012
100%
Passed
Tokens
494
Input
157
Total output
156
Reasoning within output
git_show f001
100%
Passed
Tokens
339
Input
158
Total output
155
Reasoning within output
git_show f002
0%
Failed
Tokens
342
Input
1,303
Total output
1,301
Reasoning within output
git_show f003
100%
Passed
Tokens
724
Input
244
Total output
238
Reasoning within output
git_show f004
100%
Passed
Tokens
556
Input
258
Total output
252
Reasoning within output
git_show f005
100%
Passed
Tokens
347
Input
343
Total output
341
Reasoning within output
git_show f006
100%
Passed
Tokens
356
Input
219
Total output
218
Reasoning within output
git_show f007
100%
Passed
Tokens
341
Input
142
Total output
138
Reasoning within output
git_show f008
100%
Passed
Tokens
350
Input
311
Total output
293
Reasoning within output
git_show f009
100%
Passed
Tokens
433
Input
409
Total output
408
Reasoning within output
git_show f010
100%
Passed
Tokens
343
Input
571
Total output
570
Reasoning within output
git_show f011
100%
Passed
Tokens
369
Input
148
Total output
146
Reasoning within output
git_show f012
100%
Passed
Tokens
459
Input
206
Total output
205
Reasoning within output
merge_conflicts f001
0%
Failed
Tokens
259
Input
3,522
Total output
3,518
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
279
Input
2,329
Total output
2,322
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
252
Input
1,142
Total output
1,139
Reasoning within output
merge_conflicts f004
0%
Failed
Tokens
305
Input
1,636
Total output
1,617
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
308
Input
489
Total output
469
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
294
Input
1,790
Total output
1,771
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
299
Input
285
Total output
277
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
281
Input
257
Total output
251
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
278
Input
446
Total output
441
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
346
Input
882
Total output
858
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
317
Input
640
Total output
619
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
395
Input
689
Total output
652
Reasoning within output
rebase f001
100%
Passed
Tokens
269
Input
1,448
Total output
1,444
Reasoning within output
rebase f002
100%
Passed
Tokens
298
Input
355
Total output
348
Reasoning within output
rebase f003
100%
Passed
Tokens
274
Input
635
Total output
632
Reasoning within output
rebase f004
100%
Passed
Tokens
315
Input
1,275
Total output
1,254
Reasoning within output
rebase f005
100%
Passed
Tokens
311
Input
364
Total output
346
Reasoning within output
rebase f006
100%
Passed
Tokens
305
Input
565
Total output
546
Reasoning within output
rebase f007
100%
Passed
Tokens
300
Input
262
Total output
254
Reasoning within output
rebase f008
100%
Passed
Tokens
293
Input
432
Total output
426
Reasoning within output
rebase f009
100%
Passed
Tokens
275
Input
528
Total output
523
Reasoning within output
rebase f010
100%
Passed
Tokens
373
Input
463
Total output
439
Reasoning within output
rebase f011
100%
Passed
Tokens
326
Input
431
Total output
410
Reasoning within output
rebase f012
0%
Failed
Tokens
422
Input
2,618
Total output
2,581
Reasoning within output
reflog f001
100%
Passed
Tokens
370
Input
397
Total output
375
Reasoning within output
reflog f002
100%
Passed
Tokens
379
Input
456
Total output
353
Reasoning within output
reflog f003
100%
Passed
Tokens
356
Input
286
Total output
207
Reasoning within output
reflog f004
100%
Passed
Tokens
448
Input
1,386
Total output
1,209
Reasoning within output
reflog f005
100%
Passed
Tokens
504
Input
366
Total output
224
Reasoning within output
reflog f006
100%
Passed
Tokens
388
Input
444
Total output
323
Reasoning within output
reflog f007
100%
Passed
Tokens
409
Input
596
Total output
540
Reasoning within output
reflog f008
100%
Passed
Tokens
462
Input
1,837
Total output
1,790
Reasoning within output
reflog f009
100%
Passed
Tokens
454
Input
808
Total output
674
Reasoning within output
reflog f010
100%
Passed
Tokens
413
Input
777
Total output
769
Reasoning within output
reflog f011
100%
Passed
Tokens
445
Input
1,624
Total output
1,542
Reasoning within output
reflog f012
100%
Passed
Tokens
441
Input
781
Total output
582
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
297
Input
186
Total output
161
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
427
Input
228
Total output
217
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
285
Input
149
Total output
143
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
285
Input
119
Total output
109
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
294
Input
310
Total output
275
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
340
Input
161
Total output
103
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
360
Input
203
Total output
199
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
335
Input
388
Total output
348
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
364
Input
310
Total output
295
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
292
Input
191
Total output
185
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
284
Input
332
Total output
279
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
295
Input
192
Total output
186
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
220
Input
194
Total output
186
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
265
Input
280
Total output
270
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
271
Input
895
Total output
873
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
257
Input
78
Total output
75
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
227
Input
1,441
Total output
1,416
Reasoning within output
submodule_usage f006
0%
Failed
Tokens
257
Input
753
Total output
737
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
227
Input
157
Total output
140
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
264
Input
260
Total output
255
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
259
Input
205
Total output
200
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
266
Input
344
Total output
338
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
270
Input
113
Total output
109
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
225
Input
263
Total output
252
Reasoning within output
tag_management f001
100%
Passed
Tokens
231
Input
163
Total output
157
Reasoning within output
tag_management f002
100%
Passed
Tokens
234
Input
283
Total output
266
Reasoning within output
tag_management f003
100%
Passed
Tokens
236
Input
121
Total output
112
Reasoning within output
tag_management f004
100%
Passed
Tokens
244
Input
120
Total output
118
Reasoning within output
tag_management f005
100%
Passed
Tokens
253
Input
217
Total output
210
Reasoning within output
tag_management f006
100%
Passed
Tokens
239
Input
189
Total output
179
Reasoning within output
tag_management f007
100%
Passed
Tokens
239
Input
402
Total output
392
Reasoning within output
tag_management f008
100%
Passed
Tokens
242
Input
509
Total output
488
Reasoning within output
tag_management f009
100%
Passed
Tokens
246
Input
441
Total output
426
Reasoning within output
tag_management f010
100%
Passed
Tokens
224
Input
99
Total output
92
Reasoning within output
tag_management f011
100%
Passed
Tokens
224
Input
142
Total output
137
Reasoning within output
tag_management f012
100%
Passed
Tokens
260
Input
475
Total output
466
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
297
Input
133
Total output
124
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
301
Input
569
Total output
548
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
350
Input
376
Total output
368
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
349
Input
98
Total output
94
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
293
Input
297
Total output
286
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
292
Input
152
Total output
138
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
288
Input
192
Total output
170
Reasoning within output
worktree_usage f008
100%
Passed
Tokens
315
Input
636
Total output
587
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
385
Input
129
Total output
123
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
355
Input
203
Total output
188
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
345
Input
207
Total output
199
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
293
Input
176
Total output
163
Reasoning within output