Skip to main content
BenchLM
Data

DeepSeek V4.1 Flash 1017 vs Qwen3.6-35B-A3B

Updated October 25, 2026. Rank says DeepSeek V4.1 Flash 1017 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

DeepSeek V4.1 Flash 1017 has the higher public point estimate, 65.78 versus 43.22. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
DeepSeek logo
DeepSeek V4.1 Flash 1017

DeepSeek

65.78/100

Supported · Public rank #35

90% interval 60.8–70.8

Model B
Alibaba logo
Qwen3.6-35B-A3B

Alibaba

43.22/100

Estimated · Public rank #126

Conditional range 28.9–57.6

Shared results
6
DeepSeek V4.1 Flash 1017 only
27
Qwen3.6-35B-A3B only
38
Like-for-like categories
0 / 8
Supported: DeepSeek V4.1 Flash 1017 · Estimated: Qwen3.6-35B-A3B. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    DeepSeek V4.1 Flash 1017

    DeepSeek V4.1 Flash 1017 has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Qwen3.6-35B-A3B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Qwen3.6-35B-A3B is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

61.1DeepSeek V4.1 Flash 101731.6Qwen3.6-35B-A3B

Directional only · BenchAlign v5.8

DeepSeek V4.1 Flash 1017 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
DeepSeek V4.1 Flash 1017
61.7
Supported · #24/132
Qwen3.6-35B-A3B
30.2
Estimated · #98/132
Basis
BenchAlign v5.8 lane · 11 vs 11 public rows
Reading
Directional only

Coding

Directional only
DeepSeek V4.1 Flash 1017
61.1
Supported · #18/153
Qwen3.6-35B-A3B
31.6
Estimated · #94/153
Basis
BenchAlign v5.8 lane · 8 vs 6 public rows
Reading
Directional only

Knowledge

Directional only
DeepSeek V4.1 Flash 1017
64.4
Supported · #37/187
Qwen3.6-35B-A3B
42.2
Estimated · #111/187
Basis
BenchAlign v5.8 lane · 3 vs 5 public rows
Reading
Directional only

Reasoning

Not comparable
DeepSeek V4.1 Flash 1017
82.5
Unranked · 4 rankable rows
Qwen3.6-35B-A3B
74.3
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
DeepSeek V4.1 Flash 1017
78.8
Unranked · 1 rankable row
Qwen3.6-35B-A3B
66.6
#42/56
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Multilingual

Not comparable
DeepSeek V4.1 Flash 1017
Not ranked
Qwen3.6-35B-A3B
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
DeepSeek V4.1 Flash 1017
Not ranked
Qwen3.6-35B-A3B
78.3
#63/153
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
DeepSeek V4.1 Flash 1017
70.1
Unranked · 3 rankable rows
Qwen3.6-35B-A3B
58.4
#10/12
Basis
Provisional lane · 2 vs 3 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

DeepSeek V4.1 Flash 1017
$0.0009
Fits in one request
Qwen3.6-35B-A3B
API rate not published
Fits in one request

Qwen3.6-35B-A3B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

DeepSeek V4.1 Flash 1017
$0.0186
Fits in one request
Qwen3.6-35B-A3B
API rate not published
Fits in one request

Qwen3.6-35B-A3B has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

DeepSeek V4.1 Flash 1017
$0.0192
Fits in one request
Qwen3.6-35B-A3B
API rate not published
Fits in one request
Cached-input rate unavailable

Qwen3.6-35B-A3B has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

DeepSeek V4.1 Flash 1017

1M

DeepSeek models and pricing

Qwen3.6-35B-A3B

262K

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

DeepSeek V4.1 Flash 1017

$0.006 per 1M cached input tokens

DeepSeek: Models & Pricing

Qwen3.6-35B-A3B

No comparable hosted API rate

Reasoning profile

DeepSeek V4.1 Flash 1017

Reasoning

Qwen3.6-35B-A3B

Reasoning

Weight access

DeepSeek V4.1 Flash 1017

Open Weight

Qwen3.6-35B-A3B

Open Weight

License

DeepSeek V4.1 Flash 1017

Open Weight

Qwen3.6-35B-A3B

Open Weight

Release date

DeepSeek V4.1 Flash 1017

2026-10-17

Qwen3.6-35B-A3B

2026-04-15

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
DeepSeek V4.1 Flash 1017 has the higher public point estimate, 65.78 versus 43.22. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
DeepSeek V4.1 Flash 1017 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, DeepSeek V4.1 Flash 1017 or Qwen3.6-35B-A3B?

DeepSeek V4.1 Flash 1017 has the higher public point estimate, 65.78 versus 43.22. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, DeepSeek V4.1 Flash 1017 or Qwen3.6-35B-A3B?

DeepSeek V4.1 Flash 1017 scores higher for coding on the public lane, 61.1 to 31.6. Qwen3.6-35B-A3B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, DeepSeek V4.1 Flash 1017 or Qwen3.6-35B-A3B?

DeepSeek V4.1 Flash 1017 scores higher for agentic tasks on the public lane, 61.7 to 30.2. Qwen3.6-35B-A3B is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, DeepSeek V4.1 Flash 1017 or Qwen3.6-35B-A3B?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, DeepSeek V4.1 Flash 1017 or Qwen3.6-35B-A3B?

DeepSeek V4.1 Flash 1017 has the larger documented context window: 1M, compared with 262K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

DeepSeek V4.1 Flash 1017
API / mo$1,125
Self-host / mo$27,962
Break-even1.6B/day
Qwen3.6-35B-A3B
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence71 rows

Agentic

  • Terminal-Bench 2.1

    DeepSeek V4.1 Flash 101790.6%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • terminalBench3

    DeepSeek V4.1 Flash 101730%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • Terminal-Bench 4.0

    DeepSeek V4.1 Flash 101742.30%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • CyberGym

    DeepSeek V4.1 Flash 101788.1%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • ExploitGym

    DeepSeek V4.1 Flash 101715.3%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • HLE w/ tools

    DeepSeek V4.1 Flash 101763.9%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • AutomationBench

    DeepSeek V4.1 Flash 101760.5%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • Agents' Last Exam

    DeepSeek V4.1 Flash 101735.4%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    DeepSeek V4.1 Flash 101774.5%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • CWE-bench v1

    DeepSeek V4.1 Flash 101755.0%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • MazeBench

    DeepSeek V4.1 Flash 10171%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • Terminal-Bench 2.0

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B51.5%
    Source

    Not directly comparable

  • Claw-Eval

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B68.7%
    Source

    Not directly comparable

  • QwenClawBench

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B52.6%
    Source

    Not directly comparable

  • QwenWebBench

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B1397
    Source

    Not directly comparable

  • τ³-bench results

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B67.2%
    Source

    Not directly comparable

  • VITA-Bench

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B35.6%
    Source

    Not directly comparable

  • DeepPlanning

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B25.9%
    Source

    Not directly comparable

  • Toolathlon

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B26.9%
    Source

    Not directly comparable

  • MCP Atlas

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B62.8%
    Source

    Not directly comparable

  • WideResearch

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B60.1%
    Source

    Not directly comparable

  • Gert Labs

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B42.65%
    Source

    Not directly comparable

Coding

  • Codeforces

    DeepSeek V4.1 Flash 10173471.0
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • Terminal-Bench 2.1

    DeepSeek V4.1 Flash 101790.6%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • terminalBench3

    DeepSeek V4.1 Flash 101730%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • DeepSWE

    DeepSeek V4.1 Flash 101777.0%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • ProgramBench

    DeepSeek V4.1 Flash 101729.1%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • NL2Repo

    DeepSeek V4.1 Flash 101768.2%
    Source
    Qwen3.6-35B-A3B29.4%
    Source

    DeepSeek V4.1 Flash 1017 leads this result

  • OpenHarmony Bench

    DeepSeek V4.1 Flash 101760.3%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • Bug Hunt Bench

    DeepSeek V4.1 Flash 101739.1 fixes
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • SWE-bench Verified

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B73.4%
    Source

    Not directly comparable

  • SWE Multilingual

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B67.2%
    Source

    Not directly comparable

  • SWE-bench Pro

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B49.5%
    Source

    Not directly comparable

  • Terminal-Bench 2.0

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B51.5%
    Source

    Not directly comparable

  • LiveCodeBench v6

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B80.4%
    Source

    Not directly comparable

Reasoning

  • STEMBench

    DeepSeek V4.1 Flash 10172.49
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • JevBench 1.4

    DeepSeek V4.1 Flash 10174.77
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • JevBench 1.5

    DeepSeek V4.1 Flash 10176.65
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

Multimodal

  • ExtractBench (LlamaIndex)

    Shared source
    DeepSeek V4.1 Flash 101787.11%
    Qwen3.6-35B-A3B88.11%

    Qwen3.6-35B-A3B leads this result

  • ParseBench

    Shared source
    DeepSeek V4.1 Flash 101764.56%
    Qwen3.6-35B-A3B44.10%

    DeepSeek V4.1 Flash 1017 leads this result

  • Chartography (tools)

    DeepSeek V4.1 Flash 101783.0%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • BabyVision w/ Python

    DeepSeek V4.1 Flash 101792.5%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • ZeroBench w/ Python

    DeepSeek V4.1 Flash 101751.0%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • MMMU

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B81.7%
    Source

    Not directly comparable

  • MMMU-Pro

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B75.3%
    Source

    Not directly comparable

  • RealWorldQA

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B85.3%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B89.9%
    Source

    Not directly comparable

  • CharXiv

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B78%
    Source

    Not directly comparable

  • SimpleVQA

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B58.9%
    Source

    Not directly comparable

  • CC-OCR

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B81.9%
    Source

    Not directly comparable

  • AI2D_TEST

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B92.7%
    Source

    Not directly comparable

  • RefCOCO (avg)

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B92.0%
    Source

    Not directly comparable

  • ODINW13

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B50.8%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B86.6%
    Source

    Not directly comparable

  • Video-MME (w/o subtitle)

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B82.5%
    Source

    Not directly comparable

  • VideoMMMU

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B83.7%
    Source

    Not directly comparable

  • MLVU (M-Avg)

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B86.2%
    Source

    Not directly comparable

Knowledge

  • GPQA

    DeepSeek V4.1 Flash 101790.9%
    Source
    Qwen3.6-35B-A3B86%
    Source

    DeepSeek V4.1 Flash 1017 leads this result

  • GPQA-D

    DeepSeek V4.1 Flash 101790.9%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • HLE

    DeepSeek V4.1 Flash 101742.6%
    Source
    Qwen3.6-35B-A3B21.4%
    Source

    DeepSeek V4.1 Flash 1017 leads this result

  • MMLU-Pro

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B85.2%
    Source

    Not directly comparable

  • SuperGPQA

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B64.7%
    Source

    Not directly comparable

  • C-Eval

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B90%
    Source

    Not directly comparable

Math

  • Apex

    DeepSeek V4.1 Flash 101765.6%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    DeepSeek V4.1 Flash 101767.368%
    Qwen3.6-35B-A3B20.351%

    DeepSeek V4.1 Flash 1017 leads this result

  • FrontierMath v2 (Tier 4)

    DeepSeek V4.1 Flash 101726.829%
    Source
    Qwen3.6-35B-A3B—

    Not directly comparable

  • HMMT Feb 2025

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B90.7%
    Source

    Not directly comparable

  • HMMT Nov 2025

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B89.1%
    Source

    Not directly comparable

  • HMMT Feb 2026

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B83.6%
    Source

    Not directly comparable

  • MMAnswerBench

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B78.9%
    Source

    Not directly comparable

  • AIME26

    DeepSeek V4.1 Flash 1017—
    Qwen3.6-35B-A3B92.7%
    Source

    Not directly comparable

71 public results · 6 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch DeepSeek V4.1 Flash 1017 vs Qwen3.6-35B-A3B

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 6,100+ subscribers.

Last updated October 25, 2026