LIVE
Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out03/09/26 · Anthropic|OpenAI's GPT-6 Astra on ARC-AGI-303/09/26 · OpenAI|GPT-6 Astra03/09/26 · OpenAI|OpenAI begins rolling out GPT-6 Astra03/09/26 · OpenAI|ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize03/09/26 · Anthropic|Sparks Fly: NVIDIA Accelerates Local AI at IFA 202603/09/26 · NVIDIA|Introducing WeatherNext 3, our most advanced and accurate global weather AI model03/09/26 · Google|Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly03/09/26 · Anthropic|Claude outage – Resolved03/09/26 · Anthropic|Daybreak for Frontline Defenders: $1B to protect essential services03/09/26 · OpenAI|NeoMME: an efficient Multimodal-native and Multilingual Encoder03/09/26 · Hugging Face|‘NBA 2K27’ With NVIDIA DLSS 5 Leads 28 New Games Coming to GeForce NOW03/09/26 · NVIDIA|Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out03/09/26 · Anthropic|OpenAI's GPT-6 Astra on ARC-AGI-303/09/26 · OpenAI|GPT-6 Astra03/09/26 · OpenAI|OpenAI begins rolling out GPT-6 Astra03/09/26 · OpenAI|ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize03/09/26 · Anthropic|Sparks Fly: NVIDIA Accelerates Local AI at IFA 202603/09/26 · NVIDIA|Introducing WeatherNext 3, our most advanced and accurate global weather AI model03/09/26 · Google|Porting my 1993 Amiga game to Godot, with an LLM reading the 68000 assembly03/09/26 · Anthropic|Claude outage – Resolved03/09/26 · Anthropic|Daybreak for Frontline Defenders: $1B to protect essential services03/09/26 · OpenAI|NeoMME: an efficient Multimodal-native and Multilingual Encoder03/09/26 · Hugging Face|‘NBA 2K27’ With NVIDIA DLSS 5 Leads 28 New Games Coming to GeForce NOW03/09/26 · NVIDIA|
🇨🇳 China🧠 GeneralistReleased September 2025

Qwen 3 Max

Alibaba
Free
Verdict

Strong value for high-volume usage.

Overview

Qwen 3 Max is Alibaba's open-source generalist model. Its Apache 2 license makes it fully commercially usable and self-hostable. Very strong on Asian languages (Chinese, Japanese, Korean, Thai, Vietnamese). Good on coding, decent reasoning. Preferred for multilingual apps or sovereign deployments outside the US.

Skill profile

FrenchReasoningSpeedCreativitySafety
Arena Elo1435
Verified benchmarks
GPQA64%
SWE-Bench38%
MATH88%
MMLU86%
HumanEval87.5%

What do these scores mean?

GPQA64%solid

PhD-level science questions (physics, chemistry, biology), with no tool access.

SWE-Bench38%fair

Resolving real GitHub issues under real conditions (SWE-bench Verified).

MATH88%excellent

Competition-level math problems.

MMLU86%excellent

General knowledge across dozens of academic subjects.

HumanEval87.5%excellent

Python code generation from specifications.

Strengths

  • World-class on Arena
  • Has a free tier
  • Competitive input pricing

Limitations

  • No native GDPR guarantee

Who is it for

A good fit if…
  • you want to control cost or self-host
Skip it if…
  • you handle sensitive EU data

Ideal use cases

  • Multilingual (Asian)
  • Commercial self-host
  • Asia apps
  • Coding

Access & availability

Paid API per tokenFree tier available

Key specifications

Context
256K
Input price
$0.78 $/M
Output price
$3.90 $/M
Speed
80 tok/s
Price verified Jun 1, 2026·Official sourceBenchmarks not audited

Estimate your monthly cost

Per-token API pricing
$51/ month with Qwen 3 Max

For the same usage

Indicative estimate based on standard API rates (excluding caching, batch and volume discounts). Always check the official pricing before committing.

Privacy

Not GDPR-compliantHosting : CN/selfAnonymizable data
Advanced data · for experts
Architecture, modalities, detailed cost, full benchmarks
Architecture
MoE
Size
480B (35B actifs MoE)
Cutoff date
Mar 2025
Inputs
text, image
Outputs
text, code
License
apache-2
Hosting
CN/self
Hallucination score
3/5
Estimated cost (API)
Typical exchange (~3k in / 1k out)
≈ $0.0062
1M in + 1M out
≈ $4.68
All benchmarks
Arena Elo1435
MMLU86.0%
GPQA64.0%
HumanEval87.5%
SWE-Bench38.0%
MATH88.0%

Similar models