Sakana / fugu-max
low
95.6%
195 / 204 fixtures · 1 run(s)
53,111 input / 57,121 total output / 53,467 reasoning within output tokens $0.44809050
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-1%
Text: 95.6% →
JSON: 94.6%
+4
Gained
JSON pass / text fail
−6
Lost
Text pass / JSON fail
189
Unchanged Pass
Both pass
5
Unchanged Fail
Both fail
Fixture Reliability Delta
| Fixture | Text | JSON | Delta |
|---|
Benchmark Deltas
| Benchmark | Text | JSON | Delta |
|---|---|---|---|
| branch_cleanup | 100% | 75% | -25% |
| cherry_pick | 91.7% | 83.3% | -8.3% |
| merge_conflicts | 91.7% | 83.3% | -8.3% |
| git_grep | 91.7% | 100% | + 8.3% |
| git_show | 91.7% | 100% | + 8.3% |
| worktree_usage | 91.7% | 100% | + 8.3% |
| blame_forensics | 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_log_format | 100% | 100% | + 0% |
| rebase | 83.3% | 83.3% | + 0% |
| reflog | 100% | 100% | + 0% |
| stash_recovery | 100% | 100% | + 0% |
| submodule_usage | 100% | 100% | + 0% |
| tag_management | 91.7% | 91.7% | + 0% |
Changed Fixtures (10)
Fixture Gallery (204)
blame_forensics f001
100%
Passed
Tokens
302
Input
121
Total output
114
Reasoning within output
blame_forensics f002
100%
Passed
Tokens
336
Input
231
Total output
227
Reasoning within output
blame_forensics f003
100%
Passed
Tokens
332
Input
353
Total output
345
Reasoning within output
blame_forensics f004
100%
Passed
Tokens
286
Input
105
Total output
100
Reasoning within output
blame_forensics f005
0%
Failed
Tokens
347
Input
1,129
Total output
1,124
Reasoning within output
blame_forensics f006
100%
Passed
Tokens
325
Input
213
Total output
210
Reasoning within output
blame_forensics f007
100%
Passed
Tokens
298
Input
151
Total output
147
Reasoning within output
blame_forensics f008
100%
Passed
Tokens
339
Input
170
Total output
167
Reasoning within output
blame_forensics f009
100%
Passed
Tokens
289
Input
211
Total output
208
Reasoning within output
blame_forensics f010
100%
Passed
Tokens
542
Input
178
Total output
175
Reasoning within output
blame_forensics f011
100%
Passed
Tokens
296
Input
17
Total output
12
Reasoning within output
blame_forensics f012
100%
Passed
Tokens
234
Input
215
Total output
211
Reasoning within output
branch_cleanup f001
100%
Passed
Tokens
173
Input
39
Total output
29
Reasoning within output
branch_cleanup f002
100%
Passed
Tokens
188
Input
59
Total output
48
Reasoning within output
branch_cleanup f003
100%
Passed
Tokens
171
Input
251
Total output
250
Reasoning within output
branch_cleanup f004
100%
Passed
Tokens
212
Input
203
Total output
196
Reasoning within output
branch_cleanup f005
100%
Passed
Tokens
184
Input
245
Total output
241
Reasoning within output
branch_cleanup f006
100%
Passed
Tokens
209
Input
160
Total output
150
Reasoning within output
branch_cleanup f007
100%
Passed
Tokens
184
Input
109
Total output
102
Reasoning within output
branch_cleanup f008
100%
Passed
Tokens
197
Input
127
Total output
118
Reasoning within output
branch_cleanup f009
100%
Passed
Tokens
156
Input
242
Total output
241
Reasoning within output
branch_cleanup f010
100%
Passed
Tokens
185
Input
29
Total output
18
Reasoning within output
branch_cleanup f011
100%
Passed
Tokens
144
Input
33
Total output
26
Reasoning within output
branch_cleanup f012
100%
Passed
Tokens
235
Input
241
Total output
229
Reasoning within output
cherry_pick f001
100%
Passed
Tokens
171
Input
33
Total output
27
Reasoning within output
cherry_pick f002
100%
Passed
Tokens
221
Input
65
Total output
55
Reasoning within output
cherry_pick f003
100%
Passed
Tokens
189
Input
157
Total output
151
Reasoning within output
cherry_pick f004
100%
Passed
Tokens
247
Input
257
Total output
230
Reasoning within output
cherry_pick f005
100%
Passed
Tokens
235
Input
145
Total output
125
Reasoning within output
cherry_pick f006
100%
Passed
Tokens
214
Input
52
Total output
25
Reasoning within output
cherry_pick f007
100%
Passed
Tokens
231
Input
233
Total output
222
Reasoning within output
cherry_pick f008
100%
Passed
Tokens
225
Input
42
Total output
34
Reasoning within output
cherry_pick f009
100%
Passed
Tokens
186
Input
77
Total output
72
Reasoning within output
cherry_pick f010
100%
Passed
Tokens
307
Input
719
Total output
689
Reasoning within output
cherry_pick f011
100%
Passed
Tokens
264
Input
50
Total output
27
Reasoning within output
cherry_pick f012
0%
Failed
Tokens
335
Input
79
Total output
29
Reasoning within output
commit_messages f001
82.5%
Passed
Tokens
201
Input
206
Total output
196
Reasoning within output
commit_messages f002
89%
Passed
Tokens
280
Input
25
Total output
13
Reasoning within output
commit_messages f003
92.5%
Passed
Tokens
182
Input
174
Total output
163
Reasoning within output
commit_messages f004
89%
Passed
Tokens
185
Input
7
Total output
0
Reasoning within output
commit_messages f005
91%
Passed
Tokens
197
Input
174
Total output
167
Reasoning within output
commit_messages f006
92.5%
Passed
Tokens
232
Input
365
Total output
357
Reasoning within output
commit_messages f007
87.5%
Passed
Tokens
256
Input
17
Total output
8
Reasoning within output
commit_messages f008
92.5%
Passed
Tokens
156
Input
252
Total output
247
Reasoning within output
commit_messages f009
82.5%
Passed
Tokens
220
Input
131
Total output
122
Reasoning within output
commit_messages f010
92.5%
Passed
Tokens
367
Input
9
Total output
0
Reasoning within output
commit_messages f011
92.5%
Passed
Tokens
238
Input
418
Total output
408
Reasoning within output
commit_messages f012
91.5%
Passed
Tokens
221
Input
237
Total output
229
Reasoning within output
commit_squash f001
100%
Passed
Tokens
215
Input
14
Total output
0
Reasoning within output
commit_squash f002
100%
Passed
Tokens
212
Input
204
Total output
193
Reasoning within output
commit_squash f003
100%
Passed
Tokens
201
Input
2,643
Total output
2,630
Reasoning within output
commit_squash f004
100%
Passed
Tokens
198
Input
235
Total output
222
Reasoning within output
commit_squash f005
100%
Passed
Tokens
205
Input
3,762
Total output
3,753
Reasoning within output
commit_squash f006
100%
Passed
Tokens
173
Input
358
Total output
347
Reasoning within output
commit_squash f007
100%
Passed
Tokens
179
Input
348
Total output
336
Reasoning within output
commit_squash f008
100%
Passed
Tokens
188
Input
401
Total output
389
Reasoning within output
commit_squash f009
100%
Passed
Tokens
203
Input
286
Total output
273
Reasoning within output
commit_squash f010
100%
Passed
Tokens
198
Input
26
Total output
9
Reasoning within output
commit_squash f011
100%
Passed
Tokens
225
Input
243
Total output
226
Reasoning within output
commit_squash f012
100%
Passed
Tokens
203
Input
213
Total output
193
Reasoning within output
git_bisect f001
100%
Passed
Tokens
262
Input
123
Total output
117
Reasoning within output
git_bisect f002
100%
Passed
Tokens
268
Input
9
Total output
0
Reasoning within output
git_bisect f003
100%
Passed
Tokens
264
Input
8
Total output
0
Reasoning within output
git_bisect f004
100%
Passed
Tokens
270
Input
8
Total output
0
Reasoning within output
git_bisect f005
100%
Passed
Tokens
266
Input
33
Total output
24
Reasoning within output
git_bisect f006
100%
Passed
Tokens
291
Input
9
Total output
0
Reasoning within output
git_bisect f007
100%
Passed
Tokens
262
Input
8
Total output
0
Reasoning within output
git_bisect f008
100%
Passed
Tokens
268
Input
8
Total output
0
Reasoning within output
git_bisect f009
100%
Passed
Tokens
268
Input
9
Total output
0
Reasoning within output
git_bisect f010
100%
Passed
Tokens
276
Input
10
Total output
0
Reasoning within output
git_bisect f011
100%
Passed
Tokens
272
Input
8
Total output
0
Reasoning within output
git_bisect f012
100%
Passed
Tokens
320
Input
84
Total output
77
Reasoning within output
git_clean f001
100%
Passed
Tokens
150
Input
141
Total output
131
Reasoning within output
git_clean f002
100%
Passed
Tokens
134
Input
54
Total output
44
Reasoning within output
git_clean f003
100%
Passed
Tokens
158
Input
85
Total output
79
Reasoning within output
git_clean f004
100%
Passed
Tokens
158
Input
62
Total output
55
Reasoning within output
git_clean f005
100%
Passed
Tokens
123
Input
70
Total output
58
Reasoning within output
git_clean f006
100%
Passed
Tokens
175
Input
367
Total output
359
Reasoning within output
git_clean f007
100%
Passed
Tokens
138
Input
59
Total output
42
Reasoning within output
git_clean f008
100%
Passed
Tokens
145
Input
44
Total output
34
Reasoning within output
git_clean f009
100%
Passed
Tokens
139
Input
126
Total output
112
Reasoning within output
git_clean f010
100%
Passed
Tokens
136
Input
81
Total output
71
Reasoning within output
git_clean f011
100%
Passed
Tokens
135
Input
59
Total output
48
Reasoning within output
git_clean f012
100%
Passed
Tokens
149
Input
350
Total output
343
Reasoning within output
git_grep f001
100%
Passed
Tokens
128
Input
165
Total output
160
Reasoning within output
git_grep f002
100%
Passed
Tokens
137
Input
178
Total output
177
Reasoning within output
git_grep f003
100%
Passed
Tokens
159
Input
5
Total output
0
Reasoning within output
git_grep f004
0%
Failed
Tokens
156
Input
19
Total output
10
Reasoning within output
git_grep f005
100%
Passed
Tokens
194
Input
166
Total output
165
Reasoning within output
git_grep f006
100%
Passed
Tokens
121
Input
19
Total output
16
Reasoning within output
git_grep f007
100%
Passed
Tokens
256
Input
529
Total output
527
Reasoning within output
git_grep f008
100%
Passed
Tokens
133
Input
21
Total output
14
Reasoning within output
git_grep f009
100%
Passed
Tokens
129
Input
7
Total output
0
Reasoning within output
git_grep f010
100%
Passed
Tokens
138
Input
5
Total output
0
Reasoning within output
git_grep f011
100%
Passed
Tokens
183
Input
5
Total output
0
Reasoning within output
git_grep f012
100%
Passed
Tokens
140
Input
24
Total output
10
Reasoning within output
git_log_format f001
100%
Passed
Tokens
815
Input
41
Total output
38
Reasoning within output
git_log_format f002
100%
Passed
Tokens
790
Input
95
Total output
86
Reasoning within output
git_log_format f003
100%
Passed
Tokens
652
Input
61
Total output
50
Reasoning within output
git_log_format f004
100%
Passed
Tokens
811
Input
10
Total output
7
Reasoning within output
git_log_format f005
100%
Passed
Tokens
674
Input
494
Total output
487
Reasoning within output
git_log_format f006
100%
Passed
Tokens
804
Input
67
Total output
64
Reasoning within output
git_log_format f007
100%
Passed
Tokens
816
Input
40
Total output
34
Reasoning within output
git_log_format f008
100%
Passed
Tokens
1,063
Input
37
Total output
34
Reasoning within output
git_log_format f009
100%
Passed
Tokens
667
Input
46
Total output
43
Reasoning within output
git_log_format f010
100%
Passed
Tokens
1,167
Input
36
Total output
33
Reasoning within output
git_log_format f011
100%
Passed
Tokens
521
Input
172
Total output
169
Reasoning within output
git_log_format f012
100%
Passed
Tokens
421
Input
41
Total output
38
Reasoning within output
git_show f001
100%
Passed
Tokens
245
Input
7
Total output
0
Reasoning within output
git_show f002
0%
Failed
Tokens
243
Input
524
Total output
516
Reasoning within output
git_show f003
100%
Passed
Tokens
658
Input
49
Total output
41
Reasoning within output
git_show f004
100%
Passed
Tokens
558
Input
89
Total output
82
Reasoning within output
git_show f005
100%
Passed
Tokens
252
Input
37
Total output
29
Reasoning within output
git_show f006
100%
Passed
Tokens
279
Input
77
Total output
74
Reasoning within output
git_show f007
100%
Passed
Tokens
240
Input
31
Total output
21
Reasoning within output
git_show f008
100%
Passed
Tokens
282
Input
112
Total output
84
Reasoning within output
git_show f009
100%
Passed
Tokens
358
Input
78
Total output
75
Reasoning within output
git_show f010
100%
Passed
Tokens
244
Input
18
Total output
11
Reasoning within output
git_show f011
100%
Passed
Tokens
272
Input
6
Total output
0
Reasoning within output
git_show f012
100%
Passed
Tokens
393
Input
45
Total output
42
Reasoning within output
merge_conflicts f001
100%
Passed
Tokens
162
Input
181
Total output
177
Reasoning within output
merge_conflicts f002
100%
Passed
Tokens
210
Input
622
Total output
612
Reasoning within output
merge_conflicts f003
100%
Passed
Tokens
180
Input
970
Total output
964
Reasoning within output
merge_conflicts f004
100%
Passed
Tokens
235
Input
241
Total output
214
Reasoning within output
merge_conflicts f005
100%
Passed
Tokens
220
Input
219
Total output
199
Reasoning within output
merge_conflicts f006
100%
Passed
Tokens
224
Input
322
Total output
301
Reasoning within output
merge_conflicts f007
100%
Passed
Tokens
231
Input
165
Total output
154
Reasoning within output
merge_conflicts f008
100%
Passed
Tokens
207
Input
78
Total output
70
Reasoning within output
merge_conflicts f009
100%
Passed
Tokens
205
Input
106
Total output
99
Reasoning within output
merge_conflicts f010
100%
Passed
Tokens
270
Input
579
Total output
549
Reasoning within output
merge_conflicts f011
100%
Passed
Tokens
243
Input
47
Total output
20
Reasoning within output
merge_conflicts f012
0%
Failed
Tokens
302
Input
83
Total output
41
Reasoning within output
rebase f001
100%
Passed
Tokens
172
Input
216
Total output
207
Reasoning within output
rebase f002
100%
Passed
Tokens
200
Input
22
Total output
13
Reasoning within output
rebase f003
100%
Passed
Tokens
182
Input
15
Total output
10
Reasoning within output
rebase f004
100%
Passed
Tokens
247
Input
4,839
Total output
4,815
Reasoning within output
rebase f005
100%
Passed
Tokens
225
Input
185
Total output
169
Reasoning within output
rebase f006
0%
Failed
Tokens
215
Input
200
Total output
133
Reasoning within output
rebase f007
100%
Passed
Tokens
230
Input
357
Total output
346
Reasoning within output
rebase f008
100%
Passed
Tokens
219
Input
207
Total output
199
Reasoning within output
rebase f009
100%
Passed
Tokens
202
Input
160
Total output
153
Reasoning within output
rebase f010
100%
Passed
Tokens
299
Input
490
Total output
460
Reasoning within output
rebase f011
100%
Passed
Tokens
253
Input
375
Total output
352
Reasoning within output
rebase f012
0%
Failed
Tokens
335
Input
160
Total output
108
Reasoning within output
reflog f001
100%
Passed
Tokens
318
Input
318
Total output
289
Reasoning within output
reflog f002
100%
Passed
Tokens
296
Input
194
Total output
108
Reasoning within output
reflog f003
100%
Passed
Tokens
286
Input
361
Total output
255
Reasoning within output
reflog f004
100%
Passed
Tokens
361
Input
295
Total output
158
Reasoning within output
reflog f005
100%
Passed
Tokens
392
Input
46
Total output
0
Reasoning within output
reflog f006
100%
Passed
Tokens
330
Input
588
Total output
401
Reasoning within output
reflog f007
100%
Passed
Tokens
322
Input
229
Total output
147
Reasoning within output
reflog f008
100%
Passed
Tokens
396
Input
301
Total output
215
Reasoning within output
reflog f009
100%
Passed
Tokens
356
Input
246
Total output
181
Reasoning within output
reflog f010
100%
Passed
Tokens
337
Input
2,591
Total output
2,400
Reasoning within output
reflog f011
100%
Passed
Tokens
358
Input
900
Total output
780
Reasoning within output
reflog f012
100%
Passed
Tokens
374
Input
3,572
Total output
3,386
Reasoning within output
stash_recovery f001
100%
Passed
Tokens
201
Input
9
Total output
0
Reasoning within output
stash_recovery f002
100%
Passed
Tokens
373
Input
171
Total output
120
Reasoning within output
stash_recovery f003
100%
Passed
Tokens
189
Input
9
Total output
0
Reasoning within output
stash_recovery f004
100%
Passed
Tokens
187
Input
9
Total output
0
Reasoning within output
stash_recovery f005
100%
Passed
Tokens
196
Input
9
Total output
0
Reasoning within output
stash_recovery f006
100%
Passed
Tokens
276
Input
103
Total output
98
Reasoning within output
stash_recovery f007
100%
Passed
Tokens
270
Input
14
Total output
0
Reasoning within output
stash_recovery f008
100%
Passed
Tokens
238
Input
9
Total output
0
Reasoning within output
stash_recovery f009
100%
Passed
Tokens
270
Input
49
Total output
0
Reasoning within output
stash_recovery f010
100%
Passed
Tokens
196
Input
9
Total output
0
Reasoning within output
stash_recovery f011
100%
Passed
Tokens
185
Input
9
Total output
0
Reasoning within output
stash_recovery f012
100%
Passed
Tokens
201
Input
9
Total output
0
Reasoning within output
submodule_usage f001
100%
Passed
Tokens
115
Input
150
Total output
142
Reasoning within output
submodule_usage f002
100%
Passed
Tokens
183
Input
3,259
Total output
3,250
Reasoning within output
submodule_usage f003
100%
Passed
Tokens
177
Input
254
Total output
215
Reasoning within output
submodule_usage f004
100%
Passed
Tokens
159
Input
37
Total output
27
Reasoning within output
submodule_usage f005
100%
Passed
Tokens
122
Input
1,325
Total output
1,303
Reasoning within output
submodule_usage f006
100%
Passed
Tokens
155
Input
332
Total output
322
Reasoning within output
submodule_usage f007
100%
Passed
Tokens
122
Input
217
Total output
200
Reasoning within output
submodule_usage f008
100%
Passed
Tokens
180
Input
455
Total output
447
Reasoning within output
submodule_usage f009
100%
Passed
Tokens
176
Input
174
Total output
171
Reasoning within output
submodule_usage f010
100%
Passed
Tokens
179
Input
444
Total output
439
Reasoning within output
submodule_usage f011
100%
Passed
Tokens
173
Input
25
Total output
15
Reasoning within output
submodule_usage f012
100%
Passed
Tokens
120
Input
234
Total output
223
Reasoning within output
tag_management f001
100%
Passed
Tokens
131
Input
34
Total output
22
Reasoning within output
tag_management f002
100%
Passed
Tokens
130
Input
55
Total output
31
Reasoning within output
tag_management f003
100%
Passed
Tokens
137
Input
53
Total output
38
Reasoning within output
tag_management f004
100%
Passed
Tokens
141
Input
40
Total output
32
Reasoning within output
tag_management f005
100%
Passed
Tokens
152
Input
41
Total output
27
Reasoning within output
tag_management f006
100%
Passed
Tokens
143
Input
323
Total output
310
Reasoning within output
tag_management f007
66.7%
Failed
Tokens
138
Input
453
Total output
399
Reasoning within output
tag_management f008
100%
Passed
Tokens
142
Input
326
Total output
297
Reasoning within output
tag_management f009
100%
Passed
Tokens
146
Input
63
Total output
40
Reasoning within output
tag_management f010
100%
Passed
Tokens
122
Input
33
Total output
20
Reasoning within output
tag_management f011
100%
Passed
Tokens
122
Input
48
Total output
37
Reasoning within output
tag_management f012
100%
Passed
Tokens
155
Input
100
Total output
85
Reasoning within output
worktree_usage f001
100%
Passed
Tokens
227
Input
132
Total output
123
Reasoning within output
worktree_usage f002
100%
Passed
Tokens
198
Input
122
Total output
94
Reasoning within output
worktree_usage f003
100%
Passed
Tokens
276
Input
25
Total output
15
Reasoning within output
worktree_usage f004
100%
Passed
Tokens
287
Input
106
Total output
100
Reasoning within output
worktree_usage f005
100%
Passed
Tokens
218
Input
210
Total output
195
Reasoning within output
worktree_usage f006
100%
Passed
Tokens
222
Input
231
Total output
218
Reasoning within output
worktree_usage f007
100%
Passed
Tokens
229
Input
2,059
Total output
2,036
Reasoning within output
worktree_usage f008
0%
Failed
Tokens
218
Input
217
Total output
160
Reasoning within output
worktree_usage f009
100%
Passed
Tokens
290
Input
48
Total output
38
Reasoning within output
worktree_usage f010
100%
Passed
Tokens
293
Input
151
Total output
134
Reasoning within output
worktree_usage f011
100%
Passed
Tokens
285
Input
132
Total output
122
Reasoning within output
worktree_usage f012
100%
Passed
Tokens
222
Input
1,664
Total output
1,651
Reasoning within output