Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start the free Radar Brief
BenchLM
Alibaba logo
Model A
Qwen3.6-35B-A3B

Alibaba

51.55/100

Estimated · Public rank #122

90% interval 40.0–63.1

Qwen3.6-35B-A3B vs Qwen3.6 Plus

Updated August 29, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Alibaba logo
Model B
Qwen3.6 Plus

Alibaba

64.99/100

Supported · Public rank #40

90% interval 55.6–74.3

Decision reading

Qwen3.6 Plus has the higher public score estimate, 64.99 versus 51.55, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

27 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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.

  • Agentic work

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

    Qwen3.6 Plus

    Qwen3.6 Plus leads on the same 1 weighted benchmark row.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    Qwen3.6 Plus

    Qwen3.6 Plus 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

    The category averages use different weighted benchmark sets, so they are 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

What is actually comparable

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

Shared results
27
Qwen3.6-35B-A3B only
14
Qwen3.6 Plus only
16
Like-for-like categories
3 / 8

2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Agentic

Like-for-like
Qwen3.6-35B-A3B
51.5
Qwen3.6 Plus
61.6
Weighted basis
1 vs 1 rows
Reading
Qwen3.6 Plus leads

Knowledge

Like-for-like
Qwen3.6-35B-A3B
51.4
Qwen3.6 Plus
57.1
Weighted basis
4 vs 4 rows
Reading
Qwen3.6 Plus leads

Multimodal

Like-for-like
Qwen3.6-35B-A3B
76.3
Qwen3.6 Plus
79.8
Weighted basis
2 vs 2 rows
Reading
Qwen3.6 Plus leads

Coding

Directional only
Qwen3.6-35B-A3B
73.8
Qwen3.6 Plus
70.3
Weighted basis
3 vs 2 rows
Reading
Directional only

Math

Directional only
Qwen3.6-35B-A3B
88.2
Qwen3.6 Plus
60.5
Weighted basis
2 vs 4 rows
Reading
Directional only

Reasoning

Not comparable
Qwen3.6-35B-A3B
Not measured
Qwen3.6 Plus
62.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Qwen3.6-35B-A3B
Not measured
Qwen3.6 Plus
84.7
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Qwen3.6-35B-A3B
Not measured
Qwen3.6 Plus
82.3
Weighted basis
0 vs 2 rows
Reading
Not comparable

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.

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

Qwen3.6-35B-A3B
API rate not published
Fits in one request
Qwen3.6 Plus
API rate not published
Fits in one request

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

Repository review

50K fresh input + 3K output tokens

Qwen3.6-35B-A3B
API rate not published
Fits in one request
Qwen3.6 Plus
API rate not published
Fits in one request

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

Cache-heavy agent loop

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

Qwen3.6-35B-A3B
API rate not published
Fits in one request
Cached-input rate unavailable
Qwen3.6 Plus
API rate not published
Fits in one request
Cached-input rate unavailable

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

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.

Qwen3.6-35B-A3B

262K

Qwen3.6 Plus

1M

API model ID

Qwen3.6-35B-A3B

Not sourced

Qwen3.6 Plus

Not sourced

Cached-input rate

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

Qwen3.6-35B-A3B

No comparable hosted API rate

Qwen3.6 Plus

No comparable hosted API rate

Documented inputs

Qwen3.6-35B-A3B

Not sourced

Qwen3.6 Plus

Not sourced

Documented outputs

Qwen3.6-35B-A3B

Not sourced

Qwen3.6 Plus

Not sourced

Provider availability

Qwen3.6-35B-A3B

Not sourced

Qwen3.6 Plus

Not sourced

Reasoning profile

Qwen3.6-35B-A3B

Reasoning

Qwen3.6 Plus

Reasoning

Weight access

Qwen3.6-35B-A3B

Open Weight

Qwen3.6 Plus

Proprietary

License

Qwen3.6-35B-A3B

Open Weight

Qwen3.6 Plus

Proprietary

Release date

Qwen3.6-35B-A3B

2026-04-15

Qwen3.6 Plus

2026-04-02

If you already use one of these models
Deployment change
Both entries list Alibaba as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Qwen3.6 Plus has the higher public score estimate, 64.99 versus 51.55, but the 90% score intervals overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Qwen3.6 Plus has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

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

Browse raw public benchmark evidence57 rows

Agentic

  • Terminal-Bench 2.0

    Qwen3.6-35B-A3B51.5%
    Source
    Qwen3.6 Plus61.6%
    Source

    Qwen3.6 Plus leads this result

  • Claw-Eval

    Qwen3.6-35B-A3B68.7%
    Source
    Qwen3.6 Plus58.8%
    Source

    Qwen3.6-35B-A3B leads this result

  • QwenClawBench

    Qwen3.6-35B-A3B52.6%
    Source
    Qwen3.6 Plus57.2%
    Source

    Qwen3.6 Plus leads this result

  • QwenWebBench

    Qwen3.6-35B-A3B1397
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • τ³-bench results

    Qwen3.6-35B-A3B67.2%
    Source
    Qwen3.6 Plus70.7%
    Source

    Qwen3.6 Plus leads this result

  • VITA-Bench

    Qwen3.6-35B-A3B35.6%
    Source
    Qwen3.6 Plus44.3%
    Source

    Qwen3.6 Plus leads this result

  • DeepPlanning

    Qwen3.6-35B-A3B25.9%
    Source
    Qwen3.6 Plus41.5%
    Source

    Qwen3.6 Plus leads this result

  • Toolathlon

    Qwen3.6-35B-A3B26.9%
    Source
    Qwen3.6 Plus39.8%
    Source

    Qwen3.6 Plus leads this result

  • MCP Atlas

    Qwen3.6-35B-A3B62.8%
    Source
    Qwen3.6 Plus48.2%
    Source

    Qwen3.6-35B-A3B leads this result

  • WideResearch

    Qwen3.6-35B-A3B60.1%
    Source
    Qwen3.6 Plus74.3%
    Source

    Qwen3.6 Plus leads this result

  • Gert Labs

    Shared source
    Qwen3.6-35B-A3B42.65%
    Qwen3.6 Plus50.60%

    Qwen3.6 Plus leads this result

  • MCP-Tasks

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus74.1%
    Source

    Not directly comparable

  • ResearchClawBench

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus18.0%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Qwen3.6-35B-A3B73.4%
    Source
    Qwen3.6 Plus78.8%
    Source

    Qwen3.6 Plus leads this result

  • SWE Multilingual

    Qwen3.6-35B-A3B67.2%
    Source
    Qwen3.6 Plus73.8%
    Source

    Qwen3.6 Plus leads this result

  • SWE-bench Pro

    Qwen3.6-35B-A3B49.5%
    Source
    Qwen3.6 Plus56.6%
    Source

    Qwen3.6 Plus leads this result

  • Terminal-Bench 2.0

    Qwen3.6-35B-A3B51.5%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • LiveCodeBench

    Qwen3.6-35B-A3B80.4%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • NL2Repo

    Qwen3.6-35B-A3B29.4%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • LiveCodeBench v6

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus87.1%
    Source

    Not directly comparable

  • Vibe Code Bench

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus25.56%
    Source

    Not directly comparable

Reasoning

  • AI-Needle

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus68.3%
    Source

    Not directly comparable

  • LongBench v2

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus62%
    Source

    Not directly comparable

Knowledge

  • MMLU-Pro

    Qwen3.6-35B-A3B85.2%
    Source
    Qwen3.6 Plus88.5%
    Source

    Qwen3.6 Plus leads this result

  • SuperGPQA

    Qwen3.6-35B-A3B64.7%
    Source
    Qwen3.6 Plus71.6%
    Source

    Qwen3.6 Plus leads this result

  • C-Eval

    Qwen3.6-35B-A3B90%
    Source
    Qwen3.6 Plus93.3%
    Source

    Qwen3.6 Plus leads this result

  • GPQA

    Qwen3.6-35B-A3B86%
    Source
    Qwen3.6 Plus90.4%
    Source

    Qwen3.6 Plus leads this result

  • HLE

    Qwen3.6-35B-A3B21.4%
    Source
    Qwen3.6 Plus28.8%
    Source

    Qwen3.6 Plus leads this result

  • MMLU-Redux

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus94.5%
    Source

    Not directly comparable

Math

  • HMMT Feb 2025

    Qwen3.6-35B-A3B90.7%
    Source
    Qwen3.6 Plus96.7%
    Source

    Qwen3.6 Plus leads this result

  • HMMT Nov 2025

    Qwen3.6-35B-A3B89.1%
    Source
    Qwen3.6 Plus94.6%
    Source

    Qwen3.6 Plus leads this result

  • HMMT Feb 2026

    Qwen3.6-35B-A3B83.6%
    Source
    Qwen3.6 Plus87.8%
    Source

    Qwen3.6 Plus leads this result

  • MMAnswerBench

    Qwen3.6-35B-A3B78.9%
    Source
    Qwen3.6 Plus83.8%
    Source

    Qwen3.6 Plus leads this result

  • AIME26

    Qwen3.6-35B-A3B92.7%
    Source
    Qwen3.6 Plus95.3%
    Source

    Qwen3.6 Plus leads this result

  • FrontierMath v2 (Tiers 1-3)

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus26.207%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus8.333%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus84.7%
    Source

    Not directly comparable

  • NOVA-63

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus57.9%
    Source

    Not directly comparable

Multimodal

  • MMMU

    Qwen3.6-35B-A3B81.7%
    Source
    Qwen3.6 Plus86.0%
    Source

    Qwen3.6 Plus leads this result

  • MMMU-Pro

    Qwen3.6-35B-A3B75.3%
    Source
    Qwen3.6 Plus78.8%
    Source

    Qwen3.6 Plus leads this result

  • RealWorldQA

    Qwen3.6-35B-A3B85.3%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • OmniDocBench 1.5

    Qwen3.6-35B-A3B89.9%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • CharXiv

    Qwen3.6-35B-A3B78%
    Source
    Qwen3.6 Plus81.5%
    Source

    Qwen3.6 Plus leads this result

  • SimpleVQA

    Qwen3.6-35B-A3B58.9%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • CC-OCR

    Qwen3.6-35B-A3B81.9%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • AI2D_TEST

    Qwen3.6-35B-A3B92.7%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • RefCOCO (avg)

    Qwen3.6-35B-A3B92.0%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • ODINW13

    Qwen3.6-35B-A3B50.8%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • Video-MME (with subtitle)

    Qwen3.6-35B-A3B86.6%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • Video-MME (w/o subtitle)

    Qwen3.6-35B-A3B82.5%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • VideoMMMU

    Qwen3.6-35B-A3B83.7%
    Source
    Qwen3.6 Plus84.0%
    Source

    Qwen3.6 Plus leads this result

  • MLVU (M-Avg)

    Qwen3.6-35B-A3B86.2%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • MathVision

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus88.0%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus68.2%
    Source

    Not directly comparable

  • V*

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus96.9%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus94.3%
    Source

    Not directly comparable

  • IFBench

    Qwen3.6-35B-A3B—
    Qwen3.6 Plus75.8%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus has the higher public score estimate, 64.99 versus 51.55, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Qwen3.6-35B-A3B or Qwen3.6 Plus?

The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.

Which costs less, Qwen3.6-35B-A3B or Qwen3.6 Plus?

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, Qwen3.6-35B-A3B or Qwen3.6 Plus?

Qwen3.6 Plus has the larger documented context window: 1M, compared with 262K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 29, 2026

Watch Qwen3.6-35B-A3B vs Qwen3.6 Plus

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

Read a sample issue

Join 2,000+ readers.