Qwen3.7-Max

Composite indexes

• Artificial Analysis Intelligence Index#40 of 142
  29independentv4.3.2, reasoningArtificial Analysis: Qwen3.7 Max ↗

  Leader: Claude Opus 5.5 at 58

Coding

• Terminal-Bench 4.0#41 of 88
  1.5%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Max ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#30 of 103
  74.5%independentTerminal-Bench 2.1, reasoning, AA-runArtificial Analysis: Qwen3.7 Max ↗
  74.5%vendorTerminal-Bench 2.1 (Qwen3.7-Max column in the Qwen3.8 card)Qwen3.8-2.4T-A95B model card (Hugging Face) ↗

  Leader: Claude Fable 5.1 at 91.4%

• SciCode#44 of 94
  49.5%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Max ↗

  Leader: Claude Opus 5.5 at 66.9%

• SWE-bench Pro#12 of 31
  60.6%vendorQwen-corrected task set (Qwen3.7-Max column in the Qwen3.8 card)Qwen3.8-2.4T-A95B model card (Hugging Face) ↗

  Leader: Claude Opus 5.5 at 89.9%

Agents and tool use

• τ²-Bench#10 of 88
  94.7%independenttelecom, reasoning, AA-runArtificial Analysis: Qwen3.7 Max ↗

  Leader: GLM-5.2 at 99.1%

• GDPval-AA#44 of 103
  1114independentGDPval-AA v2.1, reasoningArtificial Analysis: Qwen3.7 Max ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#23 of 142
  92.3%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Max ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#34 of 147
  40.5%independentreasoning, no tools, AA-runArtificial Analysis: Qwen3.7 Max ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#34 of 139
  13.4%independentreasoning, AA-runArtificial Analysis: Qwen3.7 Max ↗

  Leader: GPT-5.6 Sol at 32.3%

Vision and long context

• AA Long Context Reasoning#43 of 139
  79%independentreasoning, AA-LCRArtificial Analysis: Qwen3.7 Max ↗

  Leader: Kimi K3 at 88.7%

Human preference

• LMArena WebDev#35 of 54
  1517independentarena entry "qwen3.7-max-20260517", 8,376 votes, checked 2026-09-25Arena (LMArena) WebDev/Code leaderboard ↗

  Leader: Claude Opus 5.5 at 1818

Other published results