Pick Qwen3.6 35B A3B for extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost or runs at roughly 120 tokens per second on a single 24gb consumer gpu. Pick Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows or scmp reported it 'outshines larger rivals' from deepseek and moonshot on some benchmarks despite its smaller active size. On a tight budget at scale, Qwen3.6 35B A3B is the value pick.
Qwen3.6 35B A3B (Alibaba) and Step 3.7 Flash (StepFun) are two of the models people most often weigh against each other in 2026. 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. Step 3.7 Flash is stepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. 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: Step 3.7 Flash is the newer model by about 43 days (released May 29, 2026), usually meaning fresher training data and capabilities.
Specifications
Spec
Qwen3.6 35B A3B
Step 3.7 Flash
Provider
Alibaba (China)
StepFun (China)
Released
April 16, 2026
May 29, 2026
Context window
256K (~393 pages)
256K (~393 pages)
Price (in/out)
Open weight (self-host / free)
$0.2/$1.15 per 1M tokens
Open weight?
Yes — self-hostable
Yes — self-hostable
Modalities
text, image, code
text, image, code
SWE-Bench Verified
73.4%
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Extreme sparsity — only 3B of 35B parameters active per token, giving near-3B inference cost: Qwen3.6 35B A3B — Qwen3.6 35B A3B lists extreme sparsity — only 3B of 35B parameters active per token, giving near-3B inference cost among its strengths; Step 3.7 Flash does not.
Runs at roughly 120 tokens per second on a single 24GB consumer GPU: Qwen3.6 35B A3B — Qwen3.6 35B A3B lists runs at roughly 120 tokens per second on a single 24GB consumer GPU among its strengths; Step 3.7 Flash does not.
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; Step 3.7 Flash does not.
A 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows: Step 3.7 Flash — 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
SCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size: Step 3.7 Flash — StepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights — and it is the newer of the two.
Open weights (Apache 2.0) at a low per-token price: Step 3.7 Flash — Qwen3.6 35B A3B is comparatively weak here — all 35B parameters must stay resident in VRAM even though only 3B compute per token
Lowest cost at scale: Qwen3.6 35B A3B — Its weights are open, so at volume you pay for your own hardware instead of Step 3.7 Flash's $0.2/$1.15 per 1M tokens.
Which should you pick?
A cost-sensitive startup shipping high volume: Qwen3.6 35B A3B — At Open weight (self-host / free) it undercuts Step 3.7 Flash, and on millions of tokens that margin decides the monthly bill.
Anyone whose priority is extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost: Qwen3.6 35B A3B — It is specifically built for that.
Anyone whose priority is a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows: Step 3.7 Flash — That is its strongest area.
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 are real: 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.
Step 3.7 Flash: where it fits
StepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. Released May 29, 2026 by StepFun, it is built for a 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows, sCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size, open weights (Apache 2.0) at a low per-token price, and includes a 1.8B vision encoder for image understanding alongside text.
Its trade-offs: stepFun is a newer, less established lab than DeepSeek, Alibaba, or Moonshot, benchmark 'outshines rivals' claims are from press coverage of specific tests, not a full independent leaderboard sweep, and smaller ecosystem and less third-party documentation than the more established Chinese labs. At $0.2 in / $1.15 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
Qwen3.6 35B A3B and Step 3.7 Flash overlap enough that the right pick depends on your specific job. Qwen3.6 35B A3B costs less per token; and each leads in its own area — Qwen3.6 35B A3B for extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost, Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows. Rather than crowning one, run the same hard task through both once and let the results decide.
Frequently asked questions
Is Qwen3.6 35B A3B or Step 3.7 Flash better for coding?
Public SWE-Bench figures are not available for Step 3.7 Flash, so the honest test is your own repository — run an identical real bug through both. By design, Qwen3.6 35B A3B leans toward extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost while Step 3.7 Flash leans toward a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Qwen3.6 35B A3B or Step 3.7 Flash?
Qwen3.6 35B A3B is cheaper — Open weight (self-host / free) vs $0.2/$1.15 per 1M tokens.
Which has the bigger context window?
Both advertise 256K (~393 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Qwen3.6 35B A3B and Step 3.7 Flash together?
Yes — a multi-model platform like LumiChats gives you Qwen3.6 35B A3B, Step 3.7 Flash 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, Qwen3.6 35B A3B or Step 3.7 Flash?
Step 3.7 Flash — released May 29, 2026, about 43 days after Qwen3.6 35B A3B.
Qwen3.6 35B A3B vs Step 3.7 Flash
Alibaba · China | StepFun · China · Updated June 2026
Quick verdict
Pick Qwen3.6 35B A3B for extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost or runs at roughly 120 tokens per second on a single 24gb consumer gpu. Pick Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows or scmp reported it 'outshines larger rivals' from deepseek and moonshot on some benchmarks despite its smaller active size. On a tight budget at scale, Qwen3.6 35B A3B is the value pick.
Qwen3.6 35B A3B (Alibaba) and Step 3.7 Flash (StepFun) are two of the models people most often weigh against each other in 2026. 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. Step 3.7 Flash is stepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. 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: Step 3.7 Flash is the newer model by about 43 days (released May 29, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
Spec
Qwen3.6 35B A3B
Step 3.7 Flash
Provider
Alibaba (China)
StepFun (China)
Released
April 16, 2026
May 29, 2026
Context window
256K (~393 pages)
256K (~393 pages)
Price (in/out)
Open weight (self-host / free)
$0.2/$1.15 per 1M tokens
Open weight?
Yes — self-hostable
Yes — self-hostable
Modalities
text, image, code
text, image, code
SWE-Bench Verified
73.4%
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Extreme sparsity — only 3B of 35B parameters active per token, giving near-3B inference cost
Qwen3.6 35B A3B
Qwen3.6 35B A3B lists extreme sparsity — only 3B of 35B parameters active per token, giving near-3B inference cost among its strengths; Step 3.7 Flash does not.
Runs at roughly 120 tokens per second on a single 24GB consumer GPU
Qwen3.6 35B A3B
Qwen3.6 35B A3B lists runs at roughly 120 tokens per second on a single 24GB consumer GPU among its strengths; Step 3.7 Flash does not.
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; Step 3.7 Flash does not.
A 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows
Step 3.7 Flash
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
SCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size
Step 3.7 Flash
StepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights — and it is the newer of the two.
Open weights (Apache 2.0) at a low per-token price
Step 3.7 Flash
Qwen3.6 35B A3B is comparatively weak here — all 35B parameters must stay resident in VRAM even though only 3B compute per token
Lowest cost at scale
Qwen3.6 35B A3B
Its weights are open, so at volume you pay for your own hardware instead of Step 3.7 Flash's $0.2/$1.15 per 1M tokens.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Qwen3.6 35B A3B
At Open weight (self-host / free) it undercuts Step 3.7 Flash, and on millions of tokens that margin decides the monthly bill.
Anyone whose priority is extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost
→ Qwen3.6 35B A3B
It is specifically built for that.
Anyone whose priority is a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows
→ Step 3.7 Flash
That is its strongest area.
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 are real: 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.
Step 3.7 Flash: where it fits
StepFun's 198B MoE vision-language model built for coding and search agents - a distinct Chinese lab with genuinely competitive open weights. Released May 29, 2026 by StepFun, it is built for a 198B-parameter sparse MoE vision-language model (11B active) built specifically for agentic coding and search workflows, sCMP reported it 'outshines larger rivals' from DeepSeek and Moonshot on some benchmarks despite its smaller active size, open weights (Apache 2.0) at a low per-token price, and includes a 1.8B vision encoder for image understanding alongside text.
Its trade-offs: stepFun is a newer, less established lab than DeepSeek, Alibaba, or Moonshot, benchmark 'outshines rivals' claims are from press coverage of specific tests, not a full independent leaderboard sweep, and smaller ecosystem and less third-party documentation than the more established Chinese labs. At $0.2 in / $1.15 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
Qwen3.6 35B A3B and Step 3.7 Flash overlap enough that the right pick depends on your specific job. Qwen3.6 35B A3B costs less per token; and each leads in its own area — Qwen3.6 35B A3B for extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost, Step 3.7 Flash for a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both Qwen3.6 35B A3B and Step 3.7 Flash 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 Qwen3.6 35B A3B or Step 3.7 Flash better for coding?
Public SWE-Bench figures are not available for Step 3.7 Flash, so the honest test is your own repository — run an identical real bug through both. By design, Qwen3.6 35B A3B leans toward extreme sparsity — only 3b of 35b parameters active per token, giving near-3b inference cost while Step 3.7 Flash leans toward a 198b-parameter sparse moe vision-language model (11b active) built specifically for agentic coding and search workflows, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Qwen3.6 35B A3B or Step 3.7 Flash?
Qwen3.6 35B A3B is cheaper — Open weight (self-host / free) vs $0.2/$1.15 per 1M tokens.
Which has the bigger context window?
Both advertise 256K (~393 pages). Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Qwen3.6 35B A3B and Step 3.7 Flash together?
Yes — a multi-model platform like LumiChats gives you Qwen3.6 35B A3B, Step 3.7 Flash 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, Qwen3.6 35B A3B or Step 3.7 Flash?
Step 3.7 Flash — released May 29, 2026, about 43 days after Qwen3.6 35B A3B.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.