Compare / Qwen3.5-35B-A3B vs GLM 5.1

Qwen3.5-35B-A3B vs GLM 5.1

20 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.

Qwen3.5-35B-A3B
Alibaba · profile
GLM 5.1
Z.ai · profile
Results compared
20
Shared sources
3
BenchmarkMetricQwen3.5-35B-A3BGLM 5.1
Arena (formerly LMArena)reportedOverallArena rating 1,4081,456
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,4031,465
Arena (formerly LMArena)reportedCreative writingArena rating 1,3421,448
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4201,495
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3861,460
Arena (formerly LMArena)reportedOverallArena rating 1,3941,465
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3641,453
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 37.055.8
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 19.326.1
Artificial AnalysisreportedGPQA Diamond% of questions 84.5%86.8%
Artificial AnalysisreportedHumanity's Last Exam% of questions 21.0%30.1%
Artificial AnalysisreportedIFBench% of instructions 72.5%76.3%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 72.0%73.7%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 40.8%61.8%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 26.5%43.2%
Artificial AnalysisreportedΤ-bench banking% of tasks 4.9%13.6%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 89.2%97.7%
UGI LeaderboardreportedRequested-length error% off the requested word count 17.0%9.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.330.38
UGI LeaderboardreportedWriting scorescore out of 100 42.661.7

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.