Qwen3.6-27B

Composite indexes

• Artificial Analysis Intelligence Index#64 of 142
  21independentv4.3.2, reasoningArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#67 of 88
  0%independentreasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#48 of 103
  63.4%vendorTerminal-Bench 2.1, Terminus (Qwen3.6-27B column in the Qwen3.8-27B card)Qwen3.8-27B model card (Hugging Face) ↗
  60.7%independentTerminal-Bench 2.1, reasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#63 of 94
  42.8%independentreasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 66.9%

• SWE-bench Pro#22 of 31
  53.5%vendorQwen3.6-27B column in the Qwen3.8-27B cardQwen3.8-27B model card (Hugging Face) ↗

  Leader: Claude Opus 5.5 at 89.9%

Agents and tool use

• τ²-Bench#12 of 88
  94.2%independenttelecom, reasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#56 of 103
  973independentGDPval-AA v2.1, reasoningArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#61 of 142
  84.2%independentreasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#66 of 147
  23.1%independentreasoning, no tools, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#70 of 139
  1.1%independentreasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#50 of 139
  77.3%independentreasoning, AA-LCRArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#38 of 72
  74.6%independentreasoning, AA-runArtificial Analysis: Qwen3.6 27B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 87.7%

Other published results