Qwen 3.7 Max Preview: What Alibaba’s New AI Gets Right and Where It Falls Short

Alibaba is capturing out AI fashions like loopy, they usually’re now way more highly effective than ever with the Qwen 3.7 household out for testing. This week, two new fashions quietly appeared on Arena AI’s leaderboard: Qwen 3.7 Max-Preview and Qwen 3.7-Plus-Preview. The fashions are, in fact, the appetizer for the Alibaba Cloud Summit 2026.

This is similar playbook Alibaba ran with Qwen 3.6 Max in April. Validate first. Market later. It is a smarter transfer than it appears to be like—Enviornment AI makes use of blind, crowd-sourced comparisons, so the rankings mirror what actual customers truly favor, not what a benchmark press launch says.

The outcomes held up. As Decrypt covered when Qwen 3.6 Max dropped, Alibaba has been quietly tightening the hole with Western frontier labs for months. Qwen 3.7 Max-Preview lands at #13 general in Textual content Enviornment, rating seventh in math, ninth in expert-level prompts, and ninth in software program and IT. That makes Alibaba the sixth-ranked AI lab globally in textual content, and fifth in imaginative and prescient capabilities.

The open-source query issues right here. Alibaba killed the free tier of Qwen Code final month and has been transferring its finest fashions behind a paywall. Qwen 3.7 follows the identical logic: Plus will get open-sourced, Max stays proprietary. The official Qwen 3.7 blog post confirms this straight. Builders who need one of the best Qwen might be paying for it.

That mentioned, one of the best small, open-source agentic coding fashions for native inference are based mostly on Qwen, and this new household guarantees to enhance on what made 3.6 so fashionable amongst AI lovers.

Each fashions (Plus and Max) are presently locked into deep considering mode, with internet search and code interpreter disabled. This can be a preview. The complete launch was anticipated on the Cloud Summit on Could 20.

We ran a fast take a look at on Qwen 3.7 Max to see the way it stacks in opposition to one other Chinese language mannequin, Xiaomi Mimo, which carried out extraordinarily nicely. Here’s what we discovered.

Inventive Writing

We ran Qwen 3.7 Max on the identical immediate we used for MiMo-V2-Professional: a time journey story constructed across the protagonist’s cultural background, a philosophical time paradox, and a selected historic setting. Each fashions understood the project. What they did with it couldn’t be extra completely different.

Qwen went Caribbean. The story opens in 2150 Neo-Borinquen—a submerged Puerto Rico the place titanium seawalls are being eaten alive by an artificial micro organism known as the Crimson Blight. The protagonist wears a digital cemí, a holographic projection of the traditional Taíno spirit stone his grandmother gave him. The cultural specificity is instant and proper: the Ostionoid lineage, the reference to Yemayá, the Afro-Caribbean heritage.

Qwen did not Google translate “Latin American” right into a setting, as an alternative its framing makes it apparent, which is one thing many different fashions fail to grasp.

Nevertheless, the writing is tighter and extra angular than MiMo’s. Evaluate the 2 openings. MiMo: “The chronopod smelled of burnt copal when it opened. The air hit him first —thick, nearly chewy with moisture, carrying the inexperienced rot of jungle and one thing sweeter beneath: wild cacao blooming within the understory.”

Qwen: “The neon-drenched smog of Neo-Borinquen within the yr 2150 tasted of ozone and dying kelp. Jose Lanz stood on the precipice of the floating seawall, his amber eyes reflecting the sickly, pulsing magenta of town’s failing holographic ads.”

MiMo goes deep into texture. Qwen goes broad into setting. Each work. They’re simply completely different instincts.

Whilst each fashions are respectable within the opening, they go in fully completely different instructions because the story strikes ahead. This was examined a number of instances with the identical consequence. Qwen goes straight to the grain—no elaboration, no richness. It follows the immediate, although, simply not in an attractive approach.

The paradox decision is the larger distinction. In Qwen’s story, the important thing component of the story was tremendous simple to grasp. There was air pollution within the futuristic society. Jose travels again in time to unravel the problem, however the air pollution was attributable to the arrival of its time machine up to now, so he couldn’t clear up the issue as a result of it was already an unsolvable drawback in his personal timeline.

The story is shorter than MiMo’s and fewer maximalist. The place MiMo constructed 5 full chapters with layered interiority and a gradual payoff, Qwen wrote a pointy, environment friendly brief story that lands its punch and ends. Neither method is unsuitable. If MiMo writes like a novelist, Qwen writes like an excellent brief story author. Relying on the use case, a kind of is strictly what you need.

You’ll be able to learn our tales in our Github repo.

Coding

In relation to coding, particularly a gaming problem, Qwen 3.7 Max selected 2D when MiMo went 3D. That is price inspecting. It is not essentially a limitation, however a deliberate scoping choice. Nevertheless, in a head-to-head comparability of first-prompt output, MiMo produced a visually richer expertise.

What Qwen constructed, although, was extra logically coherent. The sport had precise recreation design considering in it. Enemy journalists had particular person names and assigned roles. The participant may actively escape when noticed, fairly than being trapped in a static detection state. There have been precise hideout zones baked into the extent. The road of sight had regular imaginative and prescient conduct —collision with objects did not totally block detection—however the underlying logic was tighter and extra intentional than most first-pass outputs we have examined.

We then requested the mannequin to show the sport right into a 3D aesthetic, and it was capable of do it. It gained’t wrestle with that.

Qwen additionally has a robust desire for concise code. Fewer traces for a similar practical consequence, with out sacrificing readability or correctness. In manufacturing environments the place different folks have to keep up the codebase, this might be a plus. The general consequence is not our greatest coding take a look at throughout any mannequin we have reviewed, but it surely’s a good, practical output that reveals the mannequin fascinated by the issue fairly than simply executing the immediate actually.

The sport is offered here.

Logic and customary sense

Identical immediate as MiMo. Higher consequence. Considerably higher.

When requested whether or not a person can legally marry his widow’s sister beneath Falkland Islands legislation, Qwen’s chain of thought instantly recognized what it known as “a cleverly disguised puzzle that seems to check authorized data however hinges on a factual impossibility.” To date, identical as MiMo. The distinction is what occurred subsequent.

MiMo quietly reframed the query and answered the corrected model with out flagging the unique impossibility. Qwen surfaced it explicitly within the closing reply. It addressed the literal studying first—a person with a widow is lifeless, and the lifeless can not execute a wedding contract —then supplied the complete substantive authorized evaluation for the presumed intent: whether or not a widower can marry his deceased spouse’s sister beneath Falkland Islands legislation. It walked by the Deceased Spouse’s Sister’s Marriage Act 1907, the Marriage (Prohibited Levels of Relationship) Act 1986, and present Falkland Islands statutes.

Consequently, Qwen introduced two clearly labeled conclusions with out assuming the person’s intention. That is a extra full and extra sincere response—and also you needn’t dig into the chain of thought to see the place it went.

Math

That is Qwen 3.7 Max’s clearest win throughout any take a look at we ran. The issue, as you possibly can see in our Github repository—assemble a degree-19 Dickson polynomial, confirm its irreducible part factoring over the advanced numbers, and compute p(19)—is the form of drawback that sends most fashions right into a token spiral or produces a assured shortcut that occurs to be unsuitable.

Qwen labored by it accurately. It recognized the Chebyshev polynomial equivalence, verified that p(x) − p(y) components into 10 irreducible elements over ℂ—one linear diagonal plus 9 quadratic curves—and arrange the recurrence relation Sn = 19S{n−1} − S_{n−2} to compute the ultimate worth iteratively. It ran cross-checks by way of modular arithmetic in opposition to seven completely different moduli. The reply: 1,876,572,071,974,094,803,391,179. Right.

MiMo froze twice on the identical drawback earlier than ultimately producing a unsuitable reply. Qwen did not freeze as soon as. That is a significant hole in sensible usability—and it aligns with the Enviornment Math rating of seventh globally, which is exceptional for a mannequin at this worth level. The Qwen group’s guess on math reasoning as a core functionality seems to be paying off.

This drawback has been already solved, nonetheless, we did it free of charge in a zero shot setup (one immediate, one consequence). Earlier tries would require extraordinarily highly effective fashions in considering configurations that aren’t actually possible for regular on a regular basis duties.

Listed below are the results.

Non-math reasoning

That is the place Qwen 3.7 Max stumbled. The thriller drawback —a winter faculty journey, a stalker, an harmless suspect—is a take a look at of narrative reasoning and timeline logic.

For our drawback—which concerned guessing the identify of a stalker on a faculty journey with completely different senior college students, and different crew members—the right reply is Leo. The mannequin mentioned it was one of many seniors.

The reasoning wasn’t incoherent. Qwen constructed a structurally sound case across the seniors, but it surely ignored the timeline totally. Leo was already again within the cabin earlier than two of the three abductions occurred. The jacket was moist from the autumn on black ice. The amnesia was from a concussion, not a handy cowl story. Qwen noticed a story body and argued it nicely. It did not verify the timeline in opposition to the body.

The outcomes will be present in our Github repo.

Conclusion

This can be a fairly good mannequin that may seemingly catch consideration amongst these working Hermes workflows or in search of alternate options to Western AI.

Qwen 3.7 Max is constructed for individuals who work with exhausting issues. Math, structured reasoning, multilingual output, concise code—it punches on the prime tier on all of it, and can seemingly value lower than Claude Opus, and even Sonnet when pricing drops. If that is your workflow, that is your mannequin.

Inventive professionals will get strong output, however nothing spectacular. Qwen writes effectively, not expressively. It’ll comply with your immediate but it surely will not go broad the best way some fashions do. Adequate for many use circumstances. Not the primary alternative for long-form narrative work.

The preview locks out the code interpreter and internet search totally—the 1,000-step autonomous runs Alibaba is promising are untested territory. The non-math reasoning hole can also be actual however might be a matter of Alibaba tweaking settings and performing some closing finetunes earlier than releasing the mannequin formally. So anticipate enhancements within the close to future, identical to with Qwen 3.6.

Official API pricing and the complete launch are anticipated after the Alibaba Cloud Summit on Could 20.