The Information Machine

Qwen 3.7 Max is super close to the frontier models for coding and agentic abilities.

Rohan Paul Twitter · Rohan Paul (@rohanpaul_ai) · 2026-05-21

Qwen 3.7 Max ranks 5th on Artificial Analysis benchmarks for coding and agentic tasks, placing it on par with GPT-5.4, and is now available on the AI/ML API.

Open original ↗

Appears in

Extraction

Topics: llm-benchmarksopen-source-modelsagentic-aicoding-modelsqwen

Claims

  • Qwen 3.7 Max performs on par with GPT-5.4 (xhigh) on Artificial Analysis benchmarks, ranking 5th overall.
  • Qwen 3.7 Max is now available on the AI/ML API.
  • Agent reliability is a central differentiator for Qwen 3.7 Max compared to other models.

Key quotes

Qwen 3.7 Max is super close to the frontier models for coding and agentic abilities.
on Artificial Analysis it's sitting at 5th, pretty much on par with GPT 5.4 (xhigh)