ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3.6 Max Preview vs Qwen3.5 397B-A17B vs GLM-5.1

Qwen3.5 397B-A17B comes out ahead, 65 to 57 and 54 on our weighted score, and it is the cheaper option too.

  1. Alibaba (Qwen)

    Qwen3.6 Max Preview

    Released Apr 20, 2026

    54/100
    • ECI149.2
    • Price$1.30 / $7.80
    • Context262K
    Full specs Remove Qwen3.6 Max Preview
  2. Our pick

    Alibaba (Qwen)

    Qwen3.5 397B-A17B

    Released Feb 15, 2026

    65/100
    • ECI146.7
    • Price$0.60 / $3.60
    • Context262K
    Full specs Remove Qwen3.5 397B-A17B

  3. Z.ai (Zhipu)

    GLM-5.1

    Released Apr 7, 2026

    57/100
    • ECI149.9
    • Price$1.40 / $4.40
    • Context200K
    Full specs Remove GLM-5.1
01 — Verdict

Qwen3.5 397B-A17B is our pick

Qwen3.5 397B-A17B is the better all-round choice, scoring 65/100 against GLM-5.1 (57) and Qwen3.6 Max Preview (54). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGLM-5.1Capabilities Index (ECI): GLM-5.1 149.9 · Qwen3.6 Max Preview 149.2 · Qwen3.5 397B-A17B 146.7
  • Lowest priceQwen3.5 397B-A17BQwen3.5 397B-A17B $1.35 · GLM-5.1 $2.15 · Qwen3.6 Max Preview $2.92 per 1M tokens (3:1 blend)
  • Longest contextQwen3.6 Max Preview and Qwen3.5 397B-A17BQwen3.6 Max Preview 262,144 · Qwen3.5 397B-A17B 262,144 · GLM-5.1 200,000 tokens
  • Widest inputsQwen3.5 397B-A17BQwen3.6 Max Preview: Text · Qwen3.5 397B-A17B: Text, Images, Audio, Video · GLM-5.1: Text
  • Self-hostingQwen3.5 397B-A17B and GLM-5.1Publishes downloadable weights
How the score is built
MeasureWeightQwen3.6 Max PreviewQwen3.5 397B-A17BGLM-5.1
CapabilityCapabilities Index (ECI)50%777478
Price25%284434
Inputs & features15%359045
Context window10%373732
Overall100%54/10065/10057/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Qwen3.6 Max Preview vs Qwen3.5 397B-A17B vs GLM-5.1 specifications side by side
SpecificationQwen3.6 Max PreviewAlibaba (Qwen)Qwen3.5 397B-A17BAlibaba (Qwen)GLM-5.1Z.ai (Zhipu)
Capability
Capabilities Index (ECI)149.2146.7149.9 (best)
ECI rank#54 of 148#67 of 148#51 of 148 (best)
GPQA DiamondGraduate-level science questions87.4%86.4%89.9% (best)
FrontierMath Tiers 1–3Research-level mathematics—31.2%36.8% (best)
OTIS Mock AIME 2024–2025Competition mathematics91.1%88.9%93.3% (best)
SWE-bench VerifiedFixing real GitHub issues76.7% (best)—74.2%
SimpleQA VerifiedShort factual questions52.0% (best)—34.0%
Price per million tokens
Input$1.30$0.60 (best)$1.40
Output$7.80$3.60 (best)$4.40
Cached input$0.13 (best)—$0.26
Blended (3:1)$2.92$1.35 (best)$2.15
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial Alibaba APIOfficial Z.AI API
Limits
Context window262,144 tokens (best)262,144 tokens (best)200,000 tokens
Max output65,536 tokens65,536 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoYesNo
VideoNoYesNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsProprietaryOpenOpen
API model IDqwen3.6-max-previewqwen3.5-397b-a17bglm-5.1
API providers102340 (best)
ReleasedApr 20, 2026Feb 15, 2026Apr 7, 2026
Knowledge cutoffApr 2025——
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Qwen3.6 Max Preview$28.60
  • Qwen3.5 397B-A17B$13.20
  • GLM-5.1$22.80
04 — Questions

Which should you choose?

Which is better: Qwen3.6 Max Preview, Qwen3.5 397B-A17B or GLM-5.1?

Qwen3.5 397B-A17B is the better all-round choice, scoring 65/100 against GLM-5.1 (57) and Qwen3.6 Max Preview (54). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3.6 Max Preview, Qwen3.5 397B-A17B or GLM-5.1?

Qwen3.5 397B-A17B is cheaper at $0.60 input / $3.60 output per million tokens (official Alibaba API price). GLM-5.1 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price); Qwen3.6 Max Preview costs $1.30 input / $7.80 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $1.35 per million tokens for Qwen3.5 397B-A17B versus $2.15 for GLM-5.1 (1.6× as much) and $2.92 for Qwen3.6 Max Preview (2.2× as much).

Which scores higher on benchmarks?

GLM-5.1 scores higher on the Capabilities Index (ECI): GLM-5.1 149.9 (#51 of 148), Qwen3.6 Max Preview 149.2 (#54 of 148) and Qwen3.5 397B-A17B 146.7 (#67 of 148). The confidence ranges of the top two overlap (148.0–151.6 vs 147.6–152.0), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5.1 89.9%, Qwen3.6 Max Preview 87.4%, Qwen3.5 397B-A17B 86.4%; OTIS Mock AIME 2024–2025 — GLM-5.1 93.3%, Qwen3.6 Max Preview 91.1%, Qwen3.5 397B-A17B 88.9%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3.5 397B-A17B yet, so there is no like-for-like coding score. On overall capability, GLM-5.1 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

Qwen3.6 Max Preview and Qwen3.5 397B-A17B have the largest context windows (262,144 and 262,144 tokens), against 200,000 for GLM-5.1. Maximum output per response: Qwen3.6 Max Preview up to 65,536, Qwen3.5 397B-A17B up to 65,536, GLM-5.1 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Qwen3.6 Max Preview accepts text; Qwen3.5 397B-A17B accepts text, images, audio and video; GLM-5.1 accepts text. Qwen3.5 397B-A17B handles the widest range of inputs.

Are any of these open source?

Qwen3.5 397B-A17B and GLM-5.1 publishes its weights and can be self-hosted; Qwen3.6 Max Preview is proprietary.

Which is newer?

Qwen3.6 Max Preview is the newest, released Apr 20, 2026. GLM-5.1 came out Apr 7, 2026; Qwen3.5 397B-A17B came out Feb 15, 2026. Knowledge cutoff: Qwen3.6 Max Preview Apr 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons