Compare / GPT-5 Mini vs GLM 5.2

GPT-5 Mini vs GLM 5.2

21 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.

GPT-5 Mini
OpenAI · profile
GLM 5.2
Z.ai · profile
Results compared
21
Shared sources
4
BenchmarkMetricGPT-5 MiniGLM 5.2
Arena (formerly LMArena)reportedOverallArena rating 1,3941,463
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3811,463
Arena (formerly LMArena)reportedCreative writingArena rating 1,3241,455
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4001,500
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3731,470
Arena (formerly LMArena)reportedOverallArena rating 1,3901,476
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3521,459
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 15.668.8
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 20.633.7
Artificial AnalysisreportedGPQA Diamond% of questions 82.8%89.5%
Artificial AnalysisreportedHumanity's Last Exam% of questions 21.5%41.1%
Artificial AnalysisreportedIFBench% of instructions 75.4%73.3%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 72.3%78.3%
Artificial AnalysisreportedSciCode% of problems 39.0%51.2%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 3.7%77.9%
Artificial AnalysisreportedTerminal-Bench 4.0% of tasks 0.0%1.0%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 33.3%50.8%
Artificial AnalysisreportedΤ-bench banking% of tasks 15.5%34.6%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 71.1%99.1%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 21.6%34.2%
Vending-Bench 2reportedMoney after a yearUS dollars $-31.18$8,313.78

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.