Skip to main content
BenchLM
Advertise

Model comparison

Qwen 3.6 Max (preview) vs Qwen3.6 Plus

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

Qwen 3.6 Max (preview)

Alibaba

59.3/100

Supported · Public rank #56

90% interval 40.4–78.2

Qwen3.6 Plus

Alibaba

64.4/100

Supported · Public rank #34

90% interval 55.6–73.2

Qwen3.6 Plus has the higher public score estimate, 64.41 versus 59.29, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

6 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

    Qwen 3.6 Max (preview)

    Qwen 3.6 Max (preview) 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
6
Qwen 3.6 Max (preview) only
3
Qwen3.6 Plus only
37
Like-for-like categories
1 / 8

3 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
Qwen 3.6 Max (preview)
65.4
Qwen3.6 Plus
61.6
Weighted basis
1 vs 1 rows
Reading
Qwen 3.6 Max (preview) leads

Coding

Directional only
Qwen 3.6 Max (preview)
51.0
Qwen3.6 Plus
70.3
Weighted basis
2 vs 2 rows
Reading
Directional only

Knowledge

Directional only
Qwen 3.6 Max (preview)
73.9
Qwen3.6 Plus
57.1
Weighted basis
1 vs 4 rows
Reading
Directional only

Math

Directional only
Qwen 3.6 Max (preview)
18.4
Qwen3.6 Plus
60.5
Weighted basis
2 vs 4 rows
Reading
Directional only

Reasoning

Not comparable
Qwen 3.6 Max (preview)
Not measured
Qwen3.6 Plus
62.0
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Qwen 3.6 Max (preview)
Not measured
Qwen3.6 Plus
84.7
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multimodal

Not comparable
Qwen 3.6 Max (preview)
Not measured
Qwen3.6 Plus
79.8
Weighted basis
0 vs 2 rows
Reading
Not comparable

Instruction following

Not comparable
Qwen 3.6 Max (preview)
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

Qwen 3.6 Max (preview)
API rate not published
Fits in one request
Qwen3.6 Plus
API rate not published
Fits in one request

Qwen 3.6 Max (preview) 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

Qwen 3.6 Max (preview)
API rate not published
Fits in one request
Qwen3.6 Plus
API rate not published
Fits in one request

Qwen 3.6 Max (preview) 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

Qwen 3.6 Max (preview)
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

Qwen 3.6 Max (preview) 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.

Qwen 3.6 Max (preview)

256K

Qwen3.6 Plus

1M

API model ID

Qwen 3.6 Max (preview)

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.

Qwen 3.6 Max (preview)

No comparable hosted API rate

Qwen3.6 Plus

No comparable hosted API rate

Documented inputs

Qwen 3.6 Max (preview)

Not sourced

Qwen3.6 Plus

Not sourced

Documented outputs

Qwen 3.6 Max (preview)

Not sourced

Qwen3.6 Plus

Not sourced

Provider availability

Qwen 3.6 Max (preview)

Not sourced

Qwen3.6 Plus

Not sourced

Reasoning profile

Qwen 3.6 Max (preview)

Reasoning

Qwen3.6 Plus

Reasoning

Weight access

Qwen 3.6 Max (preview)

Proprietary

Qwen3.6 Plus

Proprietary

License

Qwen 3.6 Max (preview)

Proprietary

Qwen3.6 Plus

Proprietary

Release date

Qwen 3.6 Max (preview)

2026-04-20

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, 64.41 versus 59.29, 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 evidence46 rows

Agentic

  • Terminal-Bench 2.0

    Qwen 3.6 Max (preview)65.4%
    Source
    Qwen3.6 Plus61.6%
    Source

    Qwen 3.6 Max (preview) leads this result

  • QwenClawBench

    Qwen 3.6 Max (preview)59.0%
    Source
    Qwen3.6 Plus57.2%
    Source

    Qwen 3.6 Max (preview) leads this result

  • Claw-Eval

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus58.8%
    Source

    Not directly comparable

  • τ³-bench results

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus70.7%
    Source

    Not directly comparable

  • VITA-Bench

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus44.3%
    Source

    Not directly comparable

  • DeepPlanning

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus41.5%
    Source

    Not directly comparable

  • Toolathlon

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus39.8%
    Source

    Not directly comparable

  • MCP Atlas

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus48.2%
    Source

    Not directly comparable

  • MCP-Tasks

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus74.1%
    Source

    Not directly comparable

  • WideResearch

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus74.3%
    Source

    Not directly comparable

  • Gert Labs

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus50.60%
    Source

    Not directly comparable

  • ResearchClawBench

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus18.0%
    Source

    Not directly comparable

Coding

  • SWE-bench Pro

    Qwen 3.6 Max (preview)57.3%
    Source
    Qwen3.6 Plus56.6%
    Source

    Qwen 3.6 Max (preview) leads this result

  • SciCode

    Qwen 3.6 Max (preview)47%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • NL2Repo

    Qwen 3.6 Max (preview)42.9%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • Terminal-Bench 2.0

    Qwen 3.6 Max (preview)65.4%
    Source
    Qwen3.6 Plus—

    Not directly comparable

  • SWE-bench Verified

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus78.8%
    Source

    Not directly comparable

  • SWE Multilingual

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus73.8%
    Source

    Not directly comparable

  • LiveCodeBench v6

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus87.1%
    Source

    Not directly comparable

  • Vibe Code Bench

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus25.56%
    Source

    Not directly comparable

Reasoning

  • AI-Needle

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus68.3%
    Source

    Not directly comparable

  • LongBench v2

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus62%
    Source

    Not directly comparable

Knowledge

  • SuperGPQA

    Qwen 3.6 Max (preview)73.9%
    Source
    Qwen3.6 Plus71.6%
    Source

    Qwen 3.6 Max (preview) leads this result

  • GPQA

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus90.4%
    Source

    Not directly comparable

  • MMLU-Pro

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus88.5%
    Source

    Not directly comparable

  • MMLU-Redux

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus94.5%
    Source

    Not directly comparable

  • C-Eval

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus93.3%
    Source

    Not directly comparable

  • HLE

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus28.8%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Qwen 3.6 Max (preview)23.103%
    Qwen3.6 Plus26.207%

    Qwen3.6 Plus leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Qwen 3.6 Max (preview)4.167%
    Qwen3.6 Plus8.333%

    Qwen3.6 Plus leads this result

  • AIME26

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus95.3%
    Source

    Not directly comparable

  • HMMT Feb 2025

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus96.7%
    Source

    Not directly comparable

  • HMMT Nov 2025

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus94.6%
    Source

    Not directly comparable

  • HMMT Feb 2026

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus87.8%
    Source

    Not directly comparable

  • MMAnswerBench

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus83.8%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus84.7%
    Source

    Not directly comparable

  • NOVA-63

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus57.9%
    Source

    Not directly comparable

Multimodal

  • MMMU

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus86.0%
    Source

    Not directly comparable

  • MMMU-Pro

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus78.8%
    Source

    Not directly comparable

  • MathVision

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus88.0%
    Source

    Not directly comparable

  • VideoMMMU

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus84.0%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus68.2%
    Source

    Not directly comparable

  • CharXiv

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus81.5%
    Source

    Not directly comparable

  • V*

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus96.9%
    Source

    Not directly comparable

Instruction following

  • IFEval

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus94.3%
    Source

    Not directly comparable

  • IFBench

    Qwen 3.6 Max (preview)—
    Qwen3.6 Plus75.8%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Qwen 3.6 Max (preview) or Qwen3.6 Plus?

Qwen3.6 Plus has the higher public score estimate, 64.41 versus 59.29, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Qwen 3.6 Max (preview) 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, Qwen 3.6 Max (preview) or Qwen3.6 Plus?

Qwen 3.6 Max (preview) leads the like-for-like agentic tasks comparison across 1 shared weighted benchmark row.

Which costs less, Qwen 3.6 Max (preview) 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, Qwen 3.6 Max (preview) or Qwen3.6 Plus?

Qwen3.6 Plus has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 29, 2026

Watch Qwen 3.6 Max (preview) 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.