Compare / Gemini 3.8 Flash vs GLM 4.7

Gemini 3.8 Flash vs GLM 4.7

19 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Gemini 3.8 Flash
Google · profile
GLM 4.7
Z.ai · profile
Results compared
19
Shared sources
5
BenchmarkMetricGemini 3.8 FlashGLM 4.7
Arena (formerly LMArena)reportedOverallArena rating 1,4771,444
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4821,442
Arena (formerly LMArena)reportedCreative writingArena rating 1,4821,404
Arena (formerly LMArena)reportedExpert promptsArena rating 1,5291,449
Arena (formerly LMArena)reportedInstruction followingArena rating 1,4881,425
Arena (formerly LMArena)reportedOverallArena rating 1,4921,441
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,4861,416
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 76.345.3
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 40.922.2
Artificial AnalysisreportedGPQA Diamond% of questions 95.3%85.9%
Artificial AnalysisreportedHumanity's Last Exam% of questions 47.8%27.4%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 84.0%71.0%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 87.6%45.3%
Artificial AnalysisreportedΤ-bench banking% of tasks 45.8%12.2%
SimpleQA Verified (Epoch AI)reportedCorrect answers% of questions 69.7%32.2%
UGI LeaderboardreportedRequested-length error% off the requested word count 13.0%28.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.340.38
UGI LeaderboardreportedWriting scorescore out of 100 78.547.4
Vending-Bench 2reportedMoney after a yearUS dollars $5,093.79$2,376.82

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.