Z-ai / glm-5.2 / high

Z
Z-ai / glm-5.2

high

none low medium high xhigh
96.6% 197 / 204 fixtures · 1 run(s)
36,654 input / 70,480 total output / 61,994 reasoning within output tokens $0.32146104
69.1% 141 / 204 fixtures · 1 run(s)
32,856 input / 55,835 total output / 51,259 reasoning within output tokens $0.25798495
Reliability by Benchmark (Text)
Loading reliability summary…
Text vs JSON Schema Comparison
Pass Rate Delta
-27.4% Text: 96.6% → JSON: 69.1%
+0
Gained
JSON pass / text fail
−56
Lost
Text pass / JSON fail
141
Unchanged Pass
Both pass
7
Unchanged Fail
Both fail
Fixture Reliability Delta
Fixture Text JSON Delta
Benchmark Deltas
Benchmark Text JSON Delta
branch_cleanup 100% 50% -50%
git_clean 100% 58.3% -41.7%
rebase 91.7% 58.3% -33.3%
worktree_usage 91.7% 58.3% -33.3%
commit_messages 100% 66.7% -33.3%
commit_squash 83.3% 50% -33.3%
git_grep 100% 66.7% -33.3%
git_log_format 100% 66.7% -33.3%
git_show 100% 66.7% -33.3%
blame_forensics 100% 75% -25%
stash_recovery 100% 75% -25%
tag_management 100% 75% -25%
git_bisect 100% 83.3% -16.7%
reflog 100% 83.3% -16.7%
cherry_pick 83.3% 66.7% -16.7%
merge_conflicts 91.7% 83.3% -8.3%
submodule_usage 100% 91.7% -8.3%
Changed Fixtures (56)
f005 -loss f008 -loss f009 -loss f003 -loss f005 -loss f006 -loss f008 -loss f009 -loss f011 -loss f008 -loss f010 -loss f007 -loss f010 -loss f011 -loss f012 -loss f003 -loss f004 -loss f008 -loss f010 -loss f002 -loss f007 -loss f003 -loss f005 -loss f007 -loss f011 -loss f012 -loss f002 -loss f004 -loss f007 -loss f011 -loss f004 -loss f005 -loss f008 -loss f009 -loss f002 -loss f005 -loss f007 -loss f009 -loss f009 -loss f004 -loss f008 -loss f009 -loss f010 -loss f008 -loss f012 -loss f003 -loss f005 -loss f006 -loss f011 -loss f009 -loss f010 -loss f011 -loss f003 -loss f007 -loss f009 -loss f012 -loss
Fixture Gallery (204)