SYLIN

Qwen Max

by Alibaba · Model · Language & code models

mixed

Strong on web-dev and agent rankings, but behind rivals on reasoning, terminal coding and vision.

#1 search

Now shipping: 2.4T total parameters, 71B active per token (25% fewer), image and text input, 1M-token context; output price cut from $6 to $4.50 per million

AccessAPIPrice$1.425 in · $4.275 out per M tokensContext1,000K tokensNeeds~4.8 TB (a smaller build)Size2.4T parameters

Why we say so

Arena puts Qwen 4 Max #6 on WebDev and #14 on Agent Arena, and Vals ranks it #11 overall. Artificial Analysis scores it 43 on its index, behind GPT-6.1 Sol at 46, and 48% on Terminal-Bench against Kimi K3.1's 67%. Roboflow found it underwhelming on vision, and Vals found it passes only 21.3% of legal tasks despite getting 95.7% of checklist items right. Fahd Mirza's hands-on tests were very positive, but he had early access.

Versions

VersionReleasedRank
Qwen 4 MaxLATEST
mixed Good web-dev and big efficiency gains, but trails leaders on reasoning and coding
Nov 16
Qwen 3.8 Max
strong Took #1 on Arena search, but slow at about 30 tokens/s
Jul 19#1 search

Evidence

  1. Nov 17
    On a satellite image, wrote Python to locate town labels, fixed its own Sydney/Gosford mix-up, derived scale, lapse-rate math, and flagged uncertainty; took 10+ minutes
  2. Nov 17
    Scores 48% on Terminal-Bench 4.0 against Kimi K3.1 Pro's 67%; Kimi costs $3.68 per index task
  3. Nov 17
    Placed #6 in Image-to-WebDev, just above Claude Opus 5 and GPT-6 Sol
  4. Nov 16
    Qwen4-Max launched by Alibaba; commenters say it is hosted-only with no open weights yet and describe it as a 2.4T-parameter model
  5. Nov 16
    Scores 43 on the Artificial Analysis index at $3.27 average cost; GPT-6.1 Sol (medium) scores 46 at $0.36
Show all 27
  1. Nov 16
    Leads on legal agentic work, bioinformatics and long-horizon tasks, edges ahead in agentic coding, but Claude Opus 5.5 still tops many benchmarks
  2. Nov 16
    Turned a hand-drawn doner kebab machine sketch into the best interactive HTML simulation the reviewer has seen, after 15 minutes of thinking
  3. Nov 14
    Qwen 4 Max Preview shows much better token efficiency at top reasoning and better vision, with slightly lower general intelligence than 3.8 Max
  4. Nov 11
    Noticed the seatbelt strap was under the arm in a photo, which Qwen 3.8 could not infer; gave realistic per-country enforcement answers
  5. Nov 9
    #1 on Arena search (1260)
  6. Oct 13
    #2 on Arena search (1261)
  7. Sep 20
    Larger model Occamy was said to compete with on some benchmarks
  8. Sep 6
    Post-trained further on coding and co-work; same 2.4T-parameter architecture with 1M context; beats the earlier 3.8 Max, some benchmarks by over 10 points
  9. Sep 6
    Beats Opus 5 and GPT 5.6 Sol on some agentic and knowledge-work benchmarks; not open-sourced, available via Qwen Cloud API
  10. Sep 2
    Run through Hermes Agent on a Dockerized full-stack app, it found and fixed a queue-ordering bug in one targeted pass and tested it
  11. Aug 16
    Qwen3.8-Max leaves preview as Alibaba's most capable model, a 2.4T-parameter mixture of experts aimed at long-horizon autonomous work
  12. Aug 16
    Two points below Grok 4.6 on the AA index, above DeepSeek V4, near Claude and GPT-5.6; pricier than Grok, cheaper than GPT and Claude
  13. Aug 13
    Hosted platform handles video by sampling frames plus audio, not a continuous stream; tracked three people across cuts and inferred the video's theme
  14. Aug 9
    Matches Fable 5 and GPT 5.6 Sol on some agentic software-engineering benchmarks and beats Opus 4.8
  15. Aug 9
    One point below Kimi K3 on Artificial Analysis index despite about 400B fewer parameters; API slightly pricier than Kimi
  16. Aug 4
    In one-shot 3D oil-rig landing page (Three.js+GSAP), produced the best-looking, most shippable page; reviewer says it wins on taste
  17. Aug 4
    Named winner of the bug-fix agent test on time, tokens and clean cleanup; Kimi K3 close behind, no winner on correctness
  18. Aug 3
    On the WebGL landing-page prompt, judged clearly better than DeepSeek's attempt from the prior week
  19. Jul 26
    Qwen3.8-Max-Preview, a 2.4T-parameter flagship, live on Qwen Chat and the Token Plan (Coder and Coder Work)
  20. Jul 26
    Alibaba says it is second only to Fable 5; early reports suggest it is weaker than Kimi K3
  21. Jul 19
    Reviewer found its HTML canvas railway simulation (day/night, weather, steam, no collisions) better than Fable 5's output
  22. Jul 19
    Wrote original couplets in the style of local poets across about 79 languages; reviewer found it looked good, with one invented poet

Cost to run

Alternatives

KimiFixed all bugs in about 8-9 minutes with ~17 live assertions, the most thorough checks, but left a stray booking uncleaned
GPT Sol#2 on Arena search (1258)
DeepSeek FlashFixed all bugs but took about 23 minutes, thinking longest and wasting time on browser date-picker checks; slowest, least direct
Claude Opus#3 on Arena search (1252)
Claude FableCosts $3.69 per task vs $3.14 for Fable 5, and 4-8x more than GPT, Qwen, Kimi and GLM; evaluating it cost $8,500