Pick Gemma 4 26B A4B for fast, cheap inference from a sparse moe (3.8b active of 25.2b total) or near-31b-dense quality at a fraction of the compute and memory-bandwidth cost. Pick Qwen3 235B A22B for deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux) or exceptional multilingual and alignment results (79.2 arena-hard v2, 85.2 writingbench). On a tight budget at scale, Qwen3 235B A22B is the value pick.
Gemma 4 26B A4B (Google, US) and Qwen3 235B A22B (Alibaba, China) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Gemma 4 26B A4B is an Apache-2.0 open MoE with 25.2B total but only 3.8B active parameters, delivering near-31B-dense quality at a fraction of the inference cost. 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. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.
Key differences
Context window: both advertise 256K (~393 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
Recency: Gemma 4 26B A4B is the newer model by about 9 months (released April 2, 2026), usually meaning fresher training data and capabilities.
Ecosystem: this is a US-vs-China matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Specifications
Spec
Gemma 4 26B A4B
Qwen3 235B A22B
Provider
Google (US)
Alibaba (China)
Released
April 2, 2026
July 21, 2025
Context window
256K (~393 pages)
256K (~393 pages)
Price (in/out)
$0.15/$0.6 per 1M tokens
Open weight (self-host / free)
Open weight?
Yes — self-hostable
Yes — self-hostable
Modalities
text, image, video, code
text, code
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Fast, cheap inference from a sparse MoE (3.8B active of 25.2B total): Gemma 4 26B A4B — An Apache-2.0 open MoE with 25.2B total but only 3.8B active parameters, delivering near-31B-dense quality at a fraction of the inference cost — and it is the newer of the two.
Near-31B-dense quality at a fraction of the compute and memory-bandwidth cost: Gemma 4 26B A4B — Gemma 4 26B A4B lists near-31B-dense quality at a fraction of the compute and memory-bandwidth cost among its strengths; Qwen3 235B A22B does not.
Strong reasoning and coding (88.3% AIME 2026 no-tools, 77.1% LiveCodeBench v6): Gemma 4 26B A4B — Qwen3 235B A22B is comparatively weak here — text-only with no vision, and the absence of a thinking mode caps its hardest reasoning
Deep world knowledge from 235B total parameters (83.0 MMLU-Pro, 93.1 MMLU-Redux): Qwen3 235B A22B — Gemma 4 26B A4B is comparatively weak here — all 25.2B parameters must be loaded into memory even though only 3.8B are active per token
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; Gemma 4 26B A4B 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; Gemma 4 26B A4B does not.
Lowest cost at scale: Qwen3 235B A22B — Its weights are open, so at volume you pay for your own hardware instead of Gemma 4 26B A4B's $0.15/$0.6 per 1M tokens.
Which should you pick?
A cost-sensitive startup shipping high volume: Qwen3 235B A22B — At Open weight (self-host / free) it undercuts Gemma 4 26B A4B, and on millions of tokens that margin decides the monthly bill.
Anyone whose priority is fast, cheap inference from a sparse moe (3.8b active of 25.2b total): Gemma 4 26B A4B — It is specifically built for that.
Anyone whose priority is deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux): Qwen3 235B A22B — That is its strongest area.
An enterprise with regional data-residency rules: Gemma 4 26B A4B or Qwen3 235B A22B — Origin (US vs China) affects where data is processed and which compliance regime applies — check the provider's terms for your region.
Gemma 4 26B A4B: where it fits
An Apache-2.0 open MoE with 25.2B total but only 3.8B active parameters, delivering near-31B-dense quality at a fraction of the inference cost. Released April 2, 2026 by Google, it is built for fast, cheap inference from a sparse MoE (3.8B active of 25.2B total), near-31B-dense quality at a fraction of the compute and memory-bandwidth cost, strong reasoning and coding (88.3% AIME 2026 no-tools, 77.1% LiveCodeBench v6), and multimodal input (text/image, plus video processed as frames up to 60s) with native function calling.
Its trade-offs are real: all 25.2B parameters must be loaded into memory even though only 3.8B are active per token, and 256K context trails 1M-token frontier rivals, and this variant has no audio input (audio is E2B/E4B/12B only). At $0.15 in / $0.6 out per million tokens, it sits in the budget price band.
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: 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.
The bottom line for this matchup
This is less "which is smarter" and more "which ecosystem fits." Gemma 4 26B A4B (US) and Qwen3 235B A22B (China) differ on pricing philosophy, data-residency, and tooling as much as on raw scores. Qwen3 235B A22B is the cheaper option, which matters at volume. The pragmatic move is to run one real task through both and judge the outputs against your own constraints — including where your data is allowed to be processed.
Frequently asked questions
Is Gemma 4 26B A4B or Qwen3 235B A22B better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Gemma 4 26B A4B leans toward fast, cheap inference from a sparse moe (3.8b active of 25.2b total) while Qwen3 235B A22B leans toward deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Gemma 4 26B A4B or Qwen3 235B A22B?
Qwen3 235B A22B is cheaper — $0.15/$0.6 per 1M tokens vs Open weight (self-host / free).
Which has the bigger context window?
Both advertise 256K (~393 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Gemma 4 26B A4B and Qwen3 235B A22B together?
Yes — a multi-model platform like LumiChats gives you Gemma 4 26B A4B, Qwen3 235B A22B and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Gemma 4 26B A4B or Qwen3 235B A22B?
Gemma 4 26B A4B — released April 2, 2026, about 9 months after Qwen3 235B A22B.
Gemma 4 26B A4B vs Qwen3 235B A22B
Google · US | Alibaba · China · Updated June 2026
Quick verdict
Pick Gemma 4 26B A4B for fast, cheap inference from a sparse moe (3.8b active of 25.2b total) or near-31b-dense quality at a fraction of the compute and memory-bandwidth cost. Pick Qwen3 235B A22B for deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux) or exceptional multilingual and alignment results (79.2 arena-hard v2, 85.2 writingbench). On a tight budget at scale, Qwen3 235B A22B is the value pick.
Gemma 4 26B A4B (Google, US) and Qwen3 235B A22B (Alibaba, China) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Gemma 4 26B A4B is an Apache-2.0 open MoE with 25.2B total but only 3.8B active parameters, delivering near-31B-dense quality at a fraction of the inference cost. 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. Their biggest split is price, and the breakdown below shows exactly how that plays out for your workload.
Key differences at a glance
▸Context window: both advertise 256K (~393 pages). Tie on paper — test on your own long inputs, since usable recall varies by model.
▸Recency: Gemma 4 26B A4B is the newer model by about 9 months (released April 2, 2026), usually meaning fresher training data and capabilities.
▸Ecosystem: this is a US-vs-China matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Side-by-side specs
Spec
Gemma 4 26B A4B
Qwen3 235B A22B
Provider
Google (US)
Alibaba (China)
Released
April 2, 2026
July 21, 2025
Context window
256K (~393 pages)
256K (~393 pages)
Price (in/out)
$0.15/$0.6 per 1M tokens
Open weight (self-host / free)
Open weight?
Yes — self-hostable
Yes — self-hostable
Modalities
text, image, video, code
text, code
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Fast, cheap inference from a sparse MoE (3.8B active of 25.2B total)
Gemma 4 26B A4B
An Apache-2.0 open MoE with 25.2B total but only 3.8B active parameters, delivering near-31B-dense quality at a fraction of the inference cost — and it is the newer of the two.
Near-31B-dense quality at a fraction of the compute and memory-bandwidth cost
Gemma 4 26B A4B
Gemma 4 26B A4B lists near-31B-dense quality at a fraction of the compute and memory-bandwidth cost among its strengths; Qwen3 235B A22B does not.
Qwen3 235B A22B is comparatively weak here — text-only with no vision, and the absence of a thinking mode caps its hardest reasoning
Deep world knowledge from 235B total parameters (83.0 MMLU-Pro, 93.1 MMLU-Redux)
Qwen3 235B A22B
Gemma 4 26B A4B is comparatively weak here — all 25.2B parameters must be loaded into memory even though only 3.8B are active per token
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; Gemma 4 26B A4B 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; Gemma 4 26B A4B does not.
Lowest cost at scale
Qwen3 235B A22B
Its weights are open, so at volume you pay for your own hardware instead of Gemma 4 26B A4B's $0.15/$0.6 per 1M tokens.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Qwen3 235B A22B
At Open weight (self-host / free) it undercuts Gemma 4 26B A4B, and on millions of tokens that margin decides the monthly bill.
Anyone whose priority is fast, cheap inference from a sparse moe (3.8b active of 25.2b total)
→ Gemma 4 26B A4B
It is specifically built for that.
Anyone whose priority is deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux)
→ Qwen3 235B A22B
That is its strongest area.
An enterprise with regional data-residency rules
→ Gemma 4 26B A4B or Qwen3 235B A22B
Origin (US vs China) affects where data is processed and which compliance regime applies — check the provider's terms for your region.
Gemma 4 26B A4B: where it fits
An Apache-2.0 open MoE with 25.2B total but only 3.8B active parameters, delivering near-31B-dense quality at a fraction of the inference cost. Released April 2, 2026 by Google, it is built for fast, cheap inference from a sparse MoE (3.8B active of 25.2B total), near-31B-dense quality at a fraction of the compute and memory-bandwidth cost, strong reasoning and coding (88.3% AIME 2026 no-tools, 77.1% LiveCodeBench v6), and multimodal input (text/image, plus video processed as frames up to 60s) with native function calling.
Its trade-offs are real: all 25.2B parameters must be loaded into memory even though only 3.8B are active per token, and 256K context trails 1M-token frontier rivals, and this variant has no audio input (audio is E2B/E4B/12B only). At $0.15 in / $0.6 out per million tokens, it sits in the budget price band.
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: 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.
The bottom line for this matchup
This is less "which is smarter" and more "which ecosystem fits." Gemma 4 26B A4B (US) and Qwen3 235B A22B (China) differ on pricing philosophy, data-residency, and tooling as much as on raw scores. Qwen3 235B A22B is the cheaper option, which matters at volume. The pragmatic move is to run one real task through both and judge the outputs against your own constraints — including where your data is allowed to be processed.
Want both Gemma 4 26B A4B and Qwen3 235B A22B 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.
Is Gemma 4 26B A4B or Qwen3 235B A22B better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Gemma 4 26B A4B leans toward fast, cheap inference from a sparse moe (3.8b active of 25.2b total) while Qwen3 235B A22B leans toward deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Gemma 4 26B A4B or Qwen3 235B A22B?
Qwen3 235B A22B is cheaper — $0.15/$0.6 per 1M tokens vs Open weight (self-host / free).
Which has the bigger context window?
Both advertise 256K (~393 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Gemma 4 26B A4B and Qwen3 235B A22B together?
Yes — a multi-model platform like LumiChats gives you Gemma 4 26B A4B, Qwen3 235B A22B and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Gemma 4 26B A4B or Qwen3 235B A22B?
Gemma 4 26B A4B — released April 2, 2026, about 9 months after Qwen3 235B A22B.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.