Qwen3 235B A22B vs Qwen3.6 35B A3B

Alibaba · China  |  Alibaba · China · Updated June 2026

Quick verdict

Both are Alibaba models. Qwen3.6 35B A3B is the newer, generally stronger default; reach for Qwen3 235B A22B when a specific cost or latency profile matters more than the latest capabilities.

Qwen3 235B A22B and Qwen3.6 35B A3B are both Alibaba models, so the real question is not which lab to trust but which tier fits your workload and budget. Qwen3 235B A22B is an older 235B text-only open mixture-of-experts with broad knowledge and strong writing — but no vision, no thinking mode, and weak coding. Qwen3.6 35B A3B is a sparse 35B mixture-of-experts running on 3B active parameters — strong agentic coding at near-3B cost on consumer hardware. Since both come from the same lab, the comparison below focuses on the tier-and-cost trade-offs that actually separate them.

Key differences at a glance

Side-by-side specs

SpecQwen3 235B A22BQwen3.6 35B A3B
ProviderAlibaba (China) Alibaba (China)
ReleasedJuly 21, 2025 April 16, 2026
Context window256K (~393 pages) 256K (~393 pages)
Price (in/out)Open weight (self-host / free) Open weight (self-host / free)
Open weight?Yes — self-hostable Yes — self-hostable
Modalitiestext, code text, image, code
SWE-Bench VerifiedNot published 73.4%
MRCR v2 @ 1MNot published Not published

Who wins what

Deep world knowledge from 235B total parameters (83.0 MMLU-Pro, 93.1 MMLU-Redux)

Qwen3 235B A22B

Qwen3.6 35B A3B is comparatively weak here — loses to its smaller dense sibling Qwen3.6 27B on every coding benchmark, despite more total parameters

Exceptional multilingual and alignment results (79.2 Arena-Hard v2, 85.2 WritingBench)

Qwen3 235B A22B

Qwen3 235B A22B lists exceptional multilingual and alignment results (79.2 Arena-Hard v2, 85.2 WritingBench) among its strengths; Qwen3.6 35B A3B does not.

Outstanding structured logic — 95.0 on ZebraLogic

Qwen3 235B A22B

Qwen3 235B A22B lists outstanding structured logic — 95.0 on ZebraLogic among its strengths; Qwen3.6 35B A3B does not.

Extreme sparsity — only 3B of 35B parameters active per token, giving near-3B inference cost

Qwen3.6 35B A3B

A sparse 35B mixture-of-experts running on 3B active parameters — strong agentic coding at near-3B cost on consumer hardware — and it is the newer of the two.

Runs at roughly 120 tokens per second on a single 24GB consumer GPU

Qwen3.6 35B A3B

Qwen3 235B A22B is comparatively weak here — its 235B weights need roughly 438GB in BF16, far beyond consumer hardware

Apache 2.0 weights with a 256K native context, extensible to about 1M via YaRN

Qwen3.6 35B A3B

Qwen3.6 35B A3B lists apache 2.0 weights with a 256K native context, extensible to about 1M via YaRN among its strengths; Qwen3 235B A22B does not.

Which should you pick?

Anyone whose priority is deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux)

Qwen3 235B A22B

It is specifically built for that.

Anyone whose priority is extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost

Qwen3.6 35B A3B

That is its strongest area.

Qwen3 235B A22B: where it fits

An older 235B text-only open mixture-of-experts with broad knowledge and strong writing — but no vision, no thinking mode, and weak coding. Released July 21, 2025 by Alibaba, it is built for deep world knowledge from 235B total parameters (83.0 MMLU-Pro, 93.1 MMLU-Redux), exceptional multilingual and alignment results (79.2 Arena-Hard v2, 85.2 WritingBench), outstanding structured logic — 95.0 on ZebraLogic, and no thinking mode, which makes latency and token spend entirely predictable.

Its trade-offs are real: nearly a year old and superseded — Artificial Analysis now steers users to Qwen3.5-397B instead, text-only with no vision, and the absence of a thinking mode caps its hardest reasoning, coding is weak by 2026 standards, and it publishes no SWE-Bench score to compare on, and its 235B weights need roughly 438GB in BF16, far beyond consumer hardware. As an open-weight model, its running cost is your own hardware rather than a per-token fee.

Qwen3.6 35B A3B: where it fits

A sparse 35B mixture-of-experts running on 3B active parameters — strong agentic coding at near-3B cost on consumer hardware. Released April 16, 2026 by Alibaba, it is built for extreme sparsity — only 3B of 35B parameters active per token, giving near-3B inference cost, runs at roughly 120 tokens per second on a single 24GB consumer GPU, apache 2.0 weights with a 256K native context, extensible to about 1M via YaRN, and preserves its reasoning across turns, which cuts the overhead of agentic loops.

Its trade-offs: loses to its smaller dense sibling Qwen3.6 27B on every coding benchmark, despite more total parameters, its SWE-Bench score comes from Alibaba's internal scaffold rather than the standard public harness, and all 35B parameters must stay resident in VRAM even though only 3B compute per token. As an open-weight model, its running cost is your own hardware rather than a per-token fee.

The bottom line for this matchup

Because Qwen3 235B A22B and Qwen3.6 35B A3B come from the same lab (Alibaba), they share the same training philosophy and ecosystem — the decision is purely tier vs. cost. Qwen3.6 35B A3B is the more capable, more recent option; the other earns its place only when its price or latency profile fits a specific job better. Most teams should default to Qwen3.6 35B A3B and drop down only with a concrete reason.

Want both Qwen3 235B A22B and Qwen3.6 35B A3B without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.

See pricing

Frequently asked questions

Is Qwen3 235B A22B or Qwen3.6 35B A3B better for coding?

Public SWE-Bench figures are not available for Qwen3 235B A22B, so the honest test is your own repository — run an identical real bug through both. By design, Qwen3 235B A22B leans toward deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux) while Qwen3.6 35B A3B leans toward extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost, and that positioning usually predicts which feels better on your codebase.

Which is cheaper, Qwen3 235B A22B or Qwen3.6 35B A3B?

They are priced almost identically, so cost will not decide between them.

Which has the bigger context window?

Both advertise 256K (~393 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.

Should I upgrade from Qwen3 235B A22B to Qwen3.6 35B A3B?

Since both are Alibaba models, the newer one (Qwen3.6 35B A3B) is usually the better default unless you need a specific cost or latency profile from the other.

Which is newer, Qwen3 235B A22B or Qwen3.6 35B A3B?

Qwen3.6 35B A3B — released April 16, 2026, about 9 months after Qwen3 235B A22B.

Related comparisons

Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.