Qwen3 235B A22B (2507) vs Step 5 Preview
Alibaba · China | StepFun · China · Updated June 2026
Quick verdict
Pick Qwen3 235B A22B (2507) 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). Pick Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents or 1m-token context window (64k max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available. Choose Qwen3 235B A22B (2507) if you need self-hosting or data privacy; Step 5 Preview if you want a managed API.
Qwen3 235B A22B (2507) (Alibaba) and Step 5 Preview (StepFun) are two of the models people most often weigh against each other in 2026. Qwen3 235B A22B (2507) 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. Step 5 Preview is stepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. They diverge most on price, context window and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
- ▸Cost model: Qwen3 235B A22B (2507) ships open weights you can self-host (hardware cost only, no per-token fee), while Step 5 Preview is API-metered at $1/$2.7 per 1M tokens. Your choice depends on whether you want zero marginal cost at the price of running infrastructure.
- ▸Context window: Step 5 Preview holds 3.8× more — 1M tokens (~1,500 pages) vs 256K (~393 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
- ▸Recency: Step 5 Preview is the newer model by about 14 months (released September 20, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Qwen3 235B A22B (2507) | Step 5 Preview |
|---|---|---|
| Provider | Alibaba (China) | StepFun (China) |
| Released | July 21, 2025 | September 20, 2026 |
| Context window | 256K (~393 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | Open weight (self-host / free) | $1/$2.7 per 1M tokens |
| Open weight? | Yes — self-hostable | No — API only |
| Modalities | text, code | text, image, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Deep world knowledge from 235B total parameters (83.0 MMLU-Pro, 93.1 MMLU-Redux)
Qwen3 235B A22B (2507)
An older 235B text-only open mixture-of-experts with broad knowledge and strong writing — but no vision, no thinking mode, and weak coding — and its weights are open while Step 5 Preview is API-only.
Exceptional multilingual and alignment results (79.2 Arena-Hard v2, 85.2 WritingBench)
Qwen3 235B A22B (2507)
Qwen3 235B A22B (2507) lists exceptional multilingual and alignment results (79.2 Arena-Hard v2, 85.2 WritingBench) among its strengths; Step 5 Preview does not.
Outstanding structured logic — 95.0 on ZebraLogic
Qwen3 235B A22B (2507)
Qwen3 235B A22B (2507) lists outstanding structured logic — 95.0 on ZebraLogic among its strengths; Step 5 Preview does not.
Sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents
Step 5 Preview
Its 1M tokens window holds about 3.8× more than Qwen3 235B A22B (2507)'s 256K in a single prompt.
1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available
Step 5 Preview
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October — and it carries the larger 1M tokens context.
67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%)
Step 5 Preview
Qwen3 235B A22B (2507) is comparatively weak here — its 235B weights need roughly 438GB in BF16, far beyond consumer hardware
Lowest cost at scale
Qwen3 235B A22B (2507)
Its weights are open, so at volume you pay for your own hardware instead of Step 5 Preview's $1/$2.7 per 1M tokens.
Largest single-prompt input
Step 5 Preview
Its 1M tokens window is about 3.8× larger than Qwen3 235B A22B (2507)'s 256K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Qwen3 235B A22B (2507)
At Open weight (self-host / free) it undercuts Step 5 Preview, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ Step 5 Preview
Larger 1M tokens window fits more in one prompt.
A team with data-privacy or self-hosting needs
→ Qwen3 235B A22B (2507)
Open weights let you run it on your own hardware; Step 5 Preview is API-only.
Anyone whose priority is deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux)
→ Qwen3 235B A22B (2507)
It is specifically built for that.
Anyone whose priority is sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents
→ Step 5 Preview
That is its strongest area.
Qwen3 235B A22B (2507): 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.
Step 5 Preview: where it fits
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. Released September 20, 2026 by StepFun, it is built for sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents, 1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available, 67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%), and scores 44 on the Artificial Analysis Intelligence Index, ranking 27th of 653 models tracked.
Its trade-offs: trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%, open weights were promised for October 15, 2026 but hadn't shipped as of this writing — API-only for now despite the open-weight roadmap, a 'Preview' release, not StepFun's finished flagship — positioning and pricing may change once weights ship, and stepCodeBench and DeepSWE figures are StepFun's own reported numbers, not yet independently reproduced at scale. At $1 in / $2.7 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. Qwen3 235B A22B (2507) gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Step 5 Preview gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Qwen3 235B A22B (2507) and Step 5 Preview 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 pricingFrequently asked questions
Is Qwen3 235B A22B (2507) or Step 5 Preview 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, Qwen3 235B A22B (2507) leans toward deep world knowledge from 235b total parameters (83.0 mmlu-pro, 93.1 mmlu-redux) while Step 5 Preview leans toward sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Qwen3 235B A22B (2507) or Step 5 Preview?
Qwen3 235B A22B (2507) is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Step 5 Preview is API-metered at $1/$2.7 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Step 5 Preview — 1M tokens vs 256K, about 3.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Qwen3 235B A22B (2507) and Step 5 Preview together?
Yes — a multi-model platform like LumiChats gives you Qwen3 235B A22B (2507), Step 5 Preview 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, Qwen3 235B A22B (2507) or Step 5 Preview?
Step 5 Preview — released September 20, 2026, about 14 months after Qwen3 235B A22B (2507).
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.