GLM-5.2

Composite indexes

• Artificial Analysis Intelligence Index#34 of 142
  34independentv4.3.2, reasoning, max effortArtificial Analysis: GLM-5.2 (max) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#46 of 88
  1%independentreasoning, max effort, AA-runArtificial Analysis: GLM-5.2 (max) ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#28 of 103
  81%vendorTerminal-Bench 2.1, Terminus-2GLM-5.2 model card (Hugging Face) ↗
  77.9%independentTerminal-Bench 2.1, reasoning, max effort, AA-runArtificial Analysis: GLM-5.2 (max) ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#35 of 94
  51.2%independentreasoning, max effort, AA-runArtificial Analysis: GLM-5.2 (max) ↗

  Leader: Claude Opus 5.5 at 66.9%

• SWE-bench Pro#10 of 31
  62.1%vendorOpenHands harnessGLM-5.2 model card (Hugging Face) ↗

  Leader: Claude Opus 5.5 at 89.9%

Agents and tool use

• τ²-Bench#1 of 88
  99.1%independenttelecom, reasoning, max effort, AA-runArtificial Analysis: GLM-5.2 (max) ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#33 of 103
  1358independentGDPval-AA v2.1, reasoning, max effortArtificial Analysis: GLM-5.2 (max) ↗

  Leader: Claude Opus 5.5 at 1846

• MCP Atlas#3 of 9
  76.8%vendorpublic setGLM-5.2 model card (Hugging Face) ↗

  Leader: Kimi K3 at 84.2%

Reasoning and knowledge

• GPQA Diamond#44 of 142
  91.2%vendorGLM-5.2 model card (Hugging Face) ↗
  89.5%independentreasoning, max effort, AA-runArtificial Analysis: GLM-5.2 (max) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#31 of 147
  54.7%vendorwith toolsGLM-5.2 model card (Hugging Face) ↗
  41.1%independentreasoning, max effort, no tools, AA-runArtificial Analysis: GLM-5.2 (max) ↗
  40.5%vendorno tools, text-only subsetGLM-5.2 model card (Hugging Face) ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#13 of 139
  20.9%independentreasoning, max effort, AA-runArtificial Analysis: GLM-5.2 (max) ↗

  Leader: GPT-5.6 Sol at 32.3%

• AIME 2026#2 of 13
  99.2%vendorGLM-5.2 model card (Hugging Face) ↗

  Leader: ERNIE 5.1 at 99.6%

• HMMT February 2026#1 of 8
  92.5%vendorHMMT Feb 2026GLM-5.2 model card (Hugging Face) ↗

  Leader: GLM-5.2 at 92.5%

Vision and long context

• AA Long Context Reasoning#45 of 139
  78.3%independentreasoning, max effort, AA-LCRArtificial Analysis: GLM-5.2 (max) ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#19 of 54
  1472independentarena entry "glm-5.2-max", 36,798 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#19 of 54
  1600independentarena entry "glm-5.2-max", 12,440 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results