all the models — AI benchmark observatory
← Models

Qwen3.8 Max (0902)

Alibaba Cloud / Qwen Team · open weight · qwen3.8-max-0902

Qwen3.8-Max-0902 (alias qwen3.8-max-2026-09-02) is an upgraded QwenCloud snapshot of Qwen3.8 Max, further post-trained for coding and cowork. Alibaba reports gains handling more complex engineering-scale software projects and long-horizon autonomous development, stronger collaborative agent behavior across multi-tool orchestration and end-to-end task delivery, and refined native vision understanding for chart reasoning, document parsing, and multimodal perception. It retains the 1M-token context window, thinking mode, and full tool ecosystem of Qwen3.8 Max, with a 128,000-token maximum output and a 256,000-token thinking budget. Accessible via QwenCloud as a dated, pinnable snapshot; Alibaba's changelog does not publish new quantitative benchmark scores or a model-specific price table for this snapshot.

Not enough scores for a fingerprint yet.

Benchmark scores

BenchmarkScore

No scores synced for this model.

Pricing

  • No provider pricing.

AA metrics

Intelligence
—
Speed tok/s
39.83
Blended $/M
—

Arena Elo

  • No Arena snapshot linked.