Openai / gpt-5.4-nano

none

82.8% 169 / 204 fixtures · 1 run(s)
34,160 input / 4,071 total output / 0 reasoning within output tokens $0.01192075
85.8% 175 / 204 fixtures · 1 run(s)
40,386 input / 4,687 total output / 0 reasoning within output tokens $0.01393595
Loading reliability summary…
Pass Rate Delta
+2.9% Text: 82.8% → JSON: 85.8%
+20
Gained
JSON pass / text fail
−14
Lost
Text pass / JSON fail
155
Unchanged Pass
Both pass
15
Unchanged Fail
Both fail
Fixture Reliability Delta
Fixture Text JSON Delta
Benchmark Deltas
Benchmark Text JSON Delta
commit_squash 8.3% 100% + 91.7%
branch_cleanup 100% 83.3% -16.7%
git_clean 58.3% 75% + 16.7%
merge_conflicts 75% 58.3% -16.7%
reflog 100% 83.3% -16.7%
worktree_usage 91.7% 75% -16.7%
cherry_pick 66.7% 83.3% + 16.7%
git_log_format 91.7% 83.3% -8.3%
blame_forensics 75% 83.3% + 8.3%
git_show 100% 91.7% -8.3%
submodule_usage 75% 83.3% + 8.3%
tag_management 100% 91.7% -8.3%
commit_messages 100% 100% + 0%
git_bisect 100% 100% + 0%
git_grep 91.7% 91.7% + 0%
rebase 75% 75% + 0%
stash_recovery 100% 100% + 0%
Changed Fixtures (34)