GLM-5

Composite indexes

• Artificial Analysis Intelligence Index#42 of 142
  28independentv4.3.2, reasoning (AA-estimated)Artificial Analysis: GLM-5 (Reasoning) ↗

  Leader: Claude Opus 5.5 at 58

Agents and tool use

• τ²-Bench#4 of 88
  98.2%independenttelecom, reasoning, AA-runArtificial Analysis: GLM-5 (Reasoning) ↗

  Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

• GPQA Diamond#67 of 142
  82%independentreasoning, AA-runArtificial Analysis: GLM-5 (Reasoning) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#57 of 147
  29.3%independentreasoning, no tools, AA-runArtificial Analysis: GLM-5 (Reasoning) ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#63 of 139
  2%independentreasoning, AA-runArtificial Analysis: GLM-5 (Reasoning) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#57 of 139
  75.7%independentreasoning, AA-LCRArtificial Analysis: GLM-5 (Reasoning) ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena Text#27 of 54
  1458independentarena entry "glm-5", 27,605 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

  Leader: Claude Fable 5 at 1506

• LMArena WebDev#45 of 54
  1436independentarena entry "glm-5", 7,058 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results