GLM-5.3-Flash

Composite indexes

• Artificial Analysis Intelligence Index#17 of 142
  42independentv4.3.2, reasoning, max effortArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#15 of 88
  32.8%independentreasoning, max effort, AA-runArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#18 of 103
  84.3%independentTerminal-Bench 2.1, reasoning, max effort, AA-runArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#33 of 94
  51.6%independentreasoning, max effort, AA-runArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• GDPval-AA#9 of 103
  1641independentGDPval-AA v2.1, reasoning, max effortArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#30 of 142
  91.2%independentreasoning, max effort, AA-runArtificial Analysis: GLM 5.3 Flash ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#35 of 147
  39.9%independentreasoning, max effort, no tools, AA-runArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#30 of 139
  15.4%independentreasoning, max effort, AA-runArtificial Analysis: GLM 5.3 Flash ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#31 of 139
  80%independentreasoning, max effort, AA-LCRArtificial Analysis: GLM 5.3 Flash ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#18 of 54
  1475independentarena entry "glm-5.3-flash", 10,038 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#18 of 54
  1612independentarena entry "glm-5.3-flash", 5,954 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results