Mistralai / mistral-medium-3-5
medium
95.1%
194 / 204 fixtures · 1 run(s)
42,320 input / 210,026 total output / 197,354 reasoning within output tokens $1.63867500
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
+0%
Text: 95.1% →
JSON: 95.1%
+6
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
188
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% |
| cherry_pick | 83.3% | 91.7% | + 8.3% |
| rebase | 91.7% | 83.3% | -8.3% |
| blame_forensics | 100% | 91.7% | -8.3% |
| commit_messages | 91.7% | 100% | + 8.3% |
| commit_squash | 91.7% | 100% | + 8.3% |
| git_clean | 91.7% | 100% | + 8.3% |
| reflog | 91.7% | 100% | + 8.3% |
| submodule_usage | 91.7% | 100% | + 8.3% |
| tag_management | 100% | 91.7% | -8.3% |
| git_bisect | 100% | 100% | + 0% |
| git_grep | 100% | 100% | + 0% |
| git_log_format | 100% | 100% | + 0% |
| git_show | 100% | 100% | + 0% |
| merge_conflicts | 91.7% | 91.7% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| worktree_usage | 91.7% | 91.7% | + 0% |
Changed Fixtures (12)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
258
Input
1,979
Total output
1,864
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
246
Input
519
Total output
489
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
291
Input
320
Total output
282
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
207
Input
902
Total output
753
Reasoning within output
blame_forensics f005
100%
Passed
Tokens
279
Input
11,135
Total output
9,347
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
245
Input
2,309
Total output
2,066
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
233
Input
292
Total output
249
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
260
Input
898
Total output
863
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
209
Input
345
Total output
359
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
458
Input
471
Total output
443
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
258
Input
418
Total output
369
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
157
Input
588
Total output
589
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
116
Input
166
Total output
144
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
133
Input
174
Total output
142
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
106
Input
372
Total output
392
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
146
Input
437
Total output
457
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
118
Input
240
Total output
251
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
144
Input
276
Total output
247
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
116
Input
254
Total output
264
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
136
Input
338
Total output
318
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
92
Input
275
Total output
306
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
130
Input
311
Total output
271
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
80
Input
177
Total output
221
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
175
Input
217
Total output
199
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
107
Input
2,280
Total output
2,492
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
132
Input
1,229
Total output
1,092
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
102
Input
834
Total output
952
Reasoning within output
cherry_pick f004
0%
Failed
Tokens
177
Input
4,557
Total output
4,856
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
161
Input
731
Total output
822
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
157
Input
465
Total output
377
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
154
Input
512
Total output
459
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
136
Input
194
Total output
204
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
121
Input
341
Total output
341
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
236
Input
738
Total output
744
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
177
Input
603
Total output
541
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
293
Input
1,086
Total output
1,005
Reasoning within output
commit_messages f001
93%
Passed
Tokens
121
Input
839
Total output
884
Reasoning within output
commit_messages f002
77.3%
Passed
Tokens
238
Input
5,840
Total output
6,073
Reasoning within output
commit_messages f003
93.3%
Passed
Tokens
93
Input
641
Total output
487
Reasoning within output
commit_messages f004
93.7%
Passed
Tokens
130
Input
380
Total output
355
Reasoning within output
commit_messages f005
81.7%
Passed
Tokens
115
Input
2,135
Total output
2,360
Reasoning within output
commit_messages f006
91.7%
Passed
Tokens
161
Input
958
Total output
1,011
Reasoning within output
commit_messages f007
90%
Passed
Tokens
203
Input
9,971
Total output
9,049
Reasoning within output
commit_messages f008
92.7%
Passed
Tokens
86
Input
726
Total output
677
Reasoning within output
commit_messages f009
0%
Failed
commit_messages f010
88.3%
Passed
Tokens
310
Input
10,784
Total output
10,345
Reasoning within output
commit_messages f011
85.7%
Passed
Tokens
154
Input
13,869
Total output
10,590
Reasoning within output
commit_messages f012
91.7%
Passed
Tokens
133
Input
265
Total output
319
Reasoning within output
commit_squash f001
100%
Passed
Tokens
153
Input
2,515
Total output
2,343
Reasoning within output
commit_squash f002
100%
Passed
Tokens
129
Input
621
Total output
649
Reasoning within output
commit_squash f003
100%
Passed
Tokens
140
Input
341
Total output
284
Reasoning within output
commit_squash f004
100%
Passed
Tokens
133
Input
253
Total output
224
Reasoning within output
commit_squash f005
0%
Failed
Tokens
128
Input
285
Total output
247
Reasoning within output
commit_squash f006
100%
Passed
Tokens
114
Input
343
Total output
316
Reasoning within output
commit_squash f007
100%
Passed
Tokens
115
Input
318
Total output
278
Reasoning within output
commit_squash f008
100%
Passed
Tokens
127
Input
289
Total output
266
Reasoning within output
commit_squash f009
100%
Passed
Tokens
122
Input
680
Total output
550
Reasoning within output
commit_squash f010
100%
Passed
Tokens
135
Input
515
Total output
487
Reasoning within output
commit_squash f011
100%
Passed
Tokens
143
Input
529
Total output
480
Reasoning within output
commit_squash f012
100%
Passed
Tokens
143
Input
4,888
Total output
4,879
Reasoning within output
git_bisect f001
100%
Passed
Tokens
195
Input
317
Total output
208
Reasoning within output
git_bisect f002
100%
Passed
Tokens
229
Input
484
Total output
366
Reasoning within output
git_bisect f003
100%
Passed
Tokens
219
Input
522
Total output
385
Reasoning within output
git_bisect f004
100%
Passed
Tokens
221
Input
571
Total output
479
Reasoning within output
git_bisect f005
100%
Passed
Tokens
223
Input
473
Total output
329
Reasoning within output
git_bisect f006
100%
Passed
Tokens
251
Input
405
Total output
272
Reasoning within output
git_bisect f007
100%
Passed
Tokens
223
Input
475
Total output
291
Reasoning within output
git_bisect f008
100%
Passed
Tokens
219
Input
617
Total output
422
Reasoning within output
git_bisect f009
100%
Passed
Tokens
223
Input
492
Total output
378
Reasoning within output
git_bisect f010
100%
Passed
Tokens
223
Input
543
Total output
492
Reasoning within output
git_bisect f011
100%
Passed
Tokens
223
Input
563
Total output
400
Reasoning within output
git_bisect f012
100%
Passed
Tokens
249
Input
412
Total output
332
Reasoning within output
git_clean f001
100%
Passed
Tokens
60
Input
488
Total output
479
Reasoning within output
git_clean f002
100%
Passed
Tokens
70
Input
5,921
Total output
6,555
Reasoning within output
git_clean f003
100%
Passed
Tokens
66
Input
369
Total output
410
Reasoning within output
git_clean f004
100%
Passed
Tokens
68
Input
501
Total output
533
Reasoning within output
git_clean f005
100%
Passed
Tokens
58
Input
1,038
Total output
1,133
Reasoning within output
git_clean f006
100%
Passed
Tokens
85
Input
2,733
Total output
2,899
Reasoning within output
git_clean f007
100%
Passed
Tokens
80
Input
2,665
Total output
2,911
Reasoning within output
git_clean f008
100%
Passed
Tokens
84
Input
424
Total output
436
Reasoning within output
git_clean f009
100%
Passed
Tokens
75
Input
4,741
Total output
5,425
Reasoning within output
git_clean f010
100%
Passed
Tokens
72
Input
574
Total output
640
Reasoning within output
git_clean f011
60%
Failed
Tokens
71
Input
623
Total output
648
Reasoning within output
git_clean f012
100%
Passed
Tokens
74
Input
568
Total output
587
Reasoning within output
git_grep f001
100%
Passed
Tokens
61
Input
195
Total output
212
Reasoning within output
git_grep f002
100%
Passed
Tokens
73
Input
549
Total output
593
Reasoning within output
git_grep f003
100%
Passed
Tokens
94
Input
178
Total output
188
Reasoning within output
git_grep f004
100%
Passed
Tokens
84
Input
305
Total output
280
Reasoning within output
git_grep f005
100%
Passed
Tokens
118
Input
245
Total output
234
Reasoning within output
git_grep f006
100%
Passed
Tokens
48
Input
284
Total output
307
Reasoning within output
git_grep f007
100%
Passed
Tokens
168
Input
1,443
Total output
1,303
Reasoning within output
git_grep f008
100%
Passed
Tokens
67
Input
228
Total output
239
Reasoning within output
git_grep f009
100%
Passed
Tokens
61
Input
226
Total output
200
Reasoning within output
git_grep f010
100%
Passed
Tokens
71
Input
381
Total output
368
Reasoning within output
git_grep f011
100%
Passed
Tokens
116
Input
218
Total output
228
Reasoning within output
git_grep f012
100%
Passed
Tokens
72
Input
297
Total output
298
Reasoning within output
git_log_format f001
100%
Passed
Tokens
911
Input
199
Total output
179
Reasoning within output
git_log_format f002
100%
Passed
Tokens
902
Input
456
Total output
501
Reasoning within output
git_log_format f003
100%
Passed
Tokens
734
Input
1,108
Total output
993
Reasoning within output
git_log_format f004
100%
Passed
Tokens
906
Input
624
Total output
338
Reasoning within output
git_log_format f005
100%
Passed
Tokens
747
Input
1,996
Total output
1,887
Reasoning within output
git_log_format f006
100%
Passed
Tokens
926
Input
505
Total output
299
Reasoning within output
git_log_format f007
100%
Passed
Tokens
920
Input
194
Total output
165
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,231
Input
380
Total output
303
Reasoning within output
git_log_format f009
100%
Passed
Tokens
743
Input
245
Total output
210
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,395
Input
234
Total output
222
Reasoning within output
git_log_format f011
100%
Passed
Tokens
444
Input
367
Total output
349
Reasoning within output
git_log_format f012
100%
Passed
Tokens
418
Input
164
Total output
156
Reasoning within output
git_show f001
100%
Passed
Tokens
210
Input
189
Total output
172
Reasoning within output
git_show f002
100%
Passed
Tokens
207
Input
886
Total output
931
Reasoning within output
git_show f003
100%
Passed
Tokens
680
Input
361
Total output
327
Reasoning within output
git_show f004
100%
Passed
Tokens
471
Input
187
Total output
177
Reasoning within output
git_show f005
100%
Passed
Tokens
204
Input
238
Total output
251
Reasoning within output
git_show f006
100%
Passed
Tokens
214
Input
165
Total output
143
Reasoning within output
git_show f007
100%
Passed
Tokens
204
Input
345
Total output
333
Reasoning within output
git_show f008
100%
Passed
Tokens
217
Input
286
Total output
206
Reasoning within output
git_show f009
100%
Passed
Tokens
322
Input
393
Total output
349
Reasoning within output
git_show f010
100%
Passed
Tokens
199
Input
323
Total output
326
Reasoning within output
git_show f011
100%
Passed
Tokens
234
Input
148
Total output
155
Reasoning within output
git_show f012
100%
Passed
Tokens
345
Input
198
Total output
197
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
97
Input
366
Total output
372
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
121
Input
716
Total output
650
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
91
Input
1,428
Total output
1,615
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
162
Input
2,538
Total output
2,459
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
149
Input
275
Total output
286
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
142
Input
415
Total output
355
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
152
Input
509
Total output
500
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
118
Input
296
Total output
292
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
118
Input
525
Total output
552
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
201
Input
1,469
Total output
1,512
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
155
Input
338
Total output
306
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
256
Input
1,088
Total output
982
Reasoning within output
rebase f001
100%
Passed
Tokens
110
Input
541
Total output
565
Reasoning within output
rebase f002
100%
Passed
Tokens
143
Input
237
Total output
215
Reasoning within output
rebase f003
100%
Passed
Tokens
113
Input
278
Total output
302
Reasoning within output
rebase f004
100%
Passed
Tokens
175
Input
1,214
Total output
1,209
Reasoning within output
rebase f005
100%
Passed
Tokens
154
Input
476
Total output
522
Reasoning within output
rebase f006
100%
Passed
Tokens
156
Input
581
Total output
515
Reasoning within output
rebase f007
100%
Passed
Tokens
156
Input
402
Total output
377
Reasoning within output
rebase f008
100%
Passed
Tokens
131
Input
341
Total output
360
Reasoning within output
rebase f009
100%
Passed
Tokens
116
Input
264
Total output
271
Reasoning within output
rebase f010
100%
Passed
Tokens
232
Input
809
Total output
798
Reasoning within output
rebase f011
100%
Passed
Tokens
167
Input
501
Total output
460
Reasoning within output
rebase f012
0%
Failed
Tokens
289
Input
1,108
Total output
983
Reasoning within output
reflog f001
100%
Passed
Tokens
263
Input
721
Total output
591
Reasoning within output
reflog f002
100%
Passed
Tokens
242
Input
614
Total output
342
Reasoning within output
reflog f003
100%
Passed
Tokens
220
Input
717
Total output
381
Reasoning within output
reflog f004
100%
Passed
Tokens
353
Input
4,232
Total output
3,810
Reasoning within output
reflog f005
100%
Passed
Tokens
394
Input
4,962
Total output
4,016
Reasoning within output
reflog f006
100%
Passed
Tokens
264
Input
680
Total output
299
Reasoning within output
reflog f007
100%
Passed
Tokens
313
Input
1,000
Total output
703
Reasoning within output
reflog f008
100%
Passed
Tokens
408
Input
822
Total output
358
Reasoning within output
reflog f009
100%
Passed
Tokens
348
Input
2,155
Total output
1,711
Reasoning within output
reflog f010
100%
Passed
Tokens
306
Input
1,115
Total output
854
Reasoning within output
reflog f011
100%
Passed
Tokens
363
Input
1,210
Total output
971
Reasoning within output
reflog f012
0%
Failed
Tokens
353
Input
2,834
Total output
2,319
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
148
Input
233
Total output
171
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
318
Input
362
Total output
233
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
135
Input
133
Total output
87
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
131
Input
284
Total output
225
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
143
Input
435
Total output
291
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
194
Input
233
Total output
173
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
224
Input
266
Total output
203
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
193
Input
336
Total output
233
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
228
Input
250
Total output
205
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
140
Input
166
Total output
132
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
134
Input
368
Total output
278
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
149
Input
185
Total output
146
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
51
Input
276
Total output
267
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
111
Input
1,568
Total output
1,826
Reasoning within output
submodule_usage f003
75%
Failed
Tokens
115
Input
8,082
Total output
8,805
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
102
Input
357
Total output
357
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
58
Input
592
Total output
624
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
98
Input
1,668
Total output
1,826
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
59
Input
500
Total output
514
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
109
Input
555
Total output
587
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
104
Input
323
Total output
346
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
112
Input
1,667
Total output
1,903
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
111
Input
94
Total output
95
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
58
Input
607
Total output
639
Reasoning within output
tag_management f001
100%
Passed
Tokens
68
Input
256
Total output
261
Reasoning within output
tag_management f002
100%
Passed
Tokens
64
Input
293
Total output
267
Reasoning within output
tag_management f003
100%
Passed
Tokens
73
Input
248
Total output
227
Reasoning within output
tag_management f004
100%
Passed
Tokens
80
Input
142
Total output
139
Reasoning within output
tag_management f005
100%
Passed
Tokens
93
Input
199
Total output
162
Reasoning within output
tag_management f006
100%
Passed
Tokens
75
Input
282
Total output
236
Reasoning within output
tag_management f007
100%
Passed
Tokens
73
Input
281
Total output
266
Reasoning within output
tag_management f008
100%
Passed
Tokens
77
Input
2,361
Total output
2,139
Reasoning within output
tag_management f009
100%
Passed
Tokens
78
Input
360
Total output
346
Reasoning within output
tag_management f010
100%
Passed
Tokens
57
Input
177
Total output
152
Reasoning within output
tag_management f011
100%
Passed
Tokens
60
Input
466
Total output
495
Reasoning within output
tag_management f012
100%
Passed
Tokens
99
Input
1,000
Total output
827
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
163
Input
246
Total output
224
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
166
Input
1,717
Total output
1,707
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
248
Input
977
Total output
843
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
251
Input
129
Total output
127
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
155
Input
850
Total output
818
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
157
Input
687
Total output
714
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
158
Input
649
Total output
575
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
181
Input
3,269
Total output
3,345
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
284
Input
264
Total output
286
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
251
Input
795
Total output
831
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
248
Input
258
Total output
260
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
155
Input
576
Total output
576
Reasoning within output