Qwen3.8-27B

Composite indexes

• Artificial Analysis Intelligence Index#41 of 151
  34independentv4.3.2, reasoning, xhigh effortArtificial Analysis: Qwen3.8 27B (xhigh) ↗
  20independentv4.3.2, non-reasoningArtificial Analysis: Qwen3.8 27B (Non-reasoning) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#44 of 96
  5.6%independentreasoning, xhigh effort, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗

  Leader: Claude Sonnet 5.5 at 70.6%

• Terminal-Bench 2.x#25 of 105
  79.8%independentTerminal-Bench 2.1, reasoning, xhigh effort, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗
  73%vendorTerminal-Bench 2.1, Terminus harnessQwen3.8-27B model card (Hugging Face) ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#58 of 100
  46.6%independentreasoning, xhigh effort, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗

  Leader: Claude Opus 5.5 at 66.9%

• SWE-bench Pro#13 of 33
  61.7%vendorQwen3.8-27B model card (Hugging Face) ↗

  Leader: Claude Opus 5.5 at 89.9%

• LiveCodeBench#3 of 57
  90.3%vendorLiveCodeBench v6Qwen3.8-27B model card (Hugging Face) ↗

  Leader: Fugu at 92.9%

Agents and tool use

• GDPval-AA#34 of 109
  1409independentGDPval-AA v2.1, reasoning, xhigh effortArtificial Analysis: Qwen3.8 27B (xhigh) ↗

  Leader: Muse Wonder Full at 1857

• OSWorld-Verified#2 of 21
  84.3%vendorOSWorld-VerifiedQwen3.8-27B model card (Hugging Face) ↗

  Leader: Kimi K3 at 84.8%

Reasoning and knowledge

• GPQA Diamond#36 of 144
  90.5%independentreasoning, xhigh effort, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗
  89.2%vendorQwen3.8-27B model card (Hugging Face) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#55 of 153
  33.9%independentreasoning, xhigh effort, no tools, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗
  30.8%vendorno toolsQwen3.8-27B model card (Hugging Face) ↗

  Leader: Claude Sonnet 5.5 at 64.5%

• CritPt#53 of 144
  5.4%independentreasoning, xhigh effort, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗

  Leader: Muse Wonder Full at 33%

Vision and long context

• AA Long Context Reasoning#22 of 144
  82%independentreasoning, xhigh effort, AA-LCRArtificial Analysis: Qwen3.8 27B (xhigh) ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#32 of 72
  76.3%independentreasoning, xhigh effort, AA-runArtificial Analysis: Qwen3.8 27B (xhigh) ↗

  Leader: Claude Opus 5.5 at 87.7%

Human preference

• LMArena Text#42 of 57
  1437independentarena entry "qwen3.8-27b", 10,697 votes, checked 2026-09-25Arena (LMArena) text leaderboard ↗

  Leader: Gemini 4 Argon at 1525

• LMArena WebDev#24 of 58
  1591independentarena entry "qwen3.8-27b", 9,242 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results