Qwen3.6-35B-A3B

Composite indexes

• Artificial Analysis Intelligence Index#79 of 151
  18independentv4.3.2, reasoningArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#76 of 96
  0%independentreasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Claude Sonnet 5.5 at 70.6%

• Terminal-Bench 2.x#65 of 105
  44.9%independentTerminal-Bench 2.1, reasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#84 of 100
  36.6%independentreasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 66.9%

Agents and tool use

• τ²-Bench#9 of 89
  95.3%independenttelecom, reasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#66 of 109
  879independentGDPval-AA v2.1, reasoningArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Muse Wonder Full at 1857

Reasoning and knowledge

• GPQA Diamond#65 of 144
  84.1%independentreasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#72 of 153
  22.2%independentreasoning, no tools, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Claude Sonnet 5.5 at 64.5%

• CritPt#83 of 144
  0.3%independentreasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Muse Wonder Full at 33%

Vision and long context

• AA Long Context Reasoning#74 of 144
  71.7%independentreasoning, AA-LCRArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Kimi K3 at 88.7%

• MMMU-Pro#36 of 72
  75%independentreasoning, AA-runArtificial Analysis: Qwen3.6 35B A3B (Reasoning) ↗

  Leader: Claude Opus 5.5 at 87.7%

Other published results