Alibaba

Qwen3-Max

Maker
Alibaba
Origin
China
Released
Sep 2025
Category
Language Models

Strengths & weaknesses

  • Competitive with top closed models on reasoning and coding benchmarks
  • Broad family of sizes, from edge-friendly to frontier-scale
  • Largest variant is heavy to self-host, hundreds of GB of weights
  • English-language polish lags slightly behind Western frontier labs

Evaluation

Awaiting evaluation
  • Reasoningw25—
  • Accuracyw20—
  • Long contextw15—
  • Speedw10—
  • Cost efficiencyw15—
  • Deployabilityw15—

w = weight, each criterion’s share of the overall score. How scoring works

More in Language Models

View all →
OpenAI

GPT-5.6

  • Best-in-class agentic reasoning, with search, code execution, and computer use in one API
  • Disciplined, low-hallucination output on long, multi-step tasks
  • Long-context requests above roughly 272K tokens get repriced sharply higher
  • Slower to produce a first answer than most rivals at max reasoning
Anthropic

Claude Opus 5

  • Anthropic's recommended model for complex, high-stakes work, with strong reasoning-to-cost
  • Zero-data-retention eligible, useful for regulated or enterprise deployments
  • Sits below the flagship tier in branding despite strong practical scores
  • Costs meaningfully more per token than the Sonnet tier for everyday tasks
Anthropic

Claude Sonnet 5

  • Fast and capable, priced for everyday production use
  • Strong default for coding and long documents without Opus-level cost
  • Enabling maximum thinking mode can quietly balloon token spend
  • Trails Opus on the hardest multi-step reasoning problems
Anthropic

Claude Haiku 4.5

  • Cheapest Claude tier, well suited to high-volume, simple tasks
  • Low latency, good for chat-style and classification workloads
  • No adaptive or extended thinking mode
  • Noticeably weaker on hard reasoning than Sonnet or Opus