ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3.5 397B-A17B vs Qwen3.7 Max vs GLM-5

Qwen3.5 397B-A17B comes out ahead, 65 to 58 and 55 on our weighted score, and it is the cheaper option too.

  1. 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

  2. Alibaba (Qwen)

    Qwen3.7 Max

    Released May 21, 2026

    58/100
    • ECI153.7
    • Price$2.50 / $7.50
    • Context1M
    Full specs Remove Qwen3.7 Max

  3. Z.ai (Zhipu)

    GLM-5

    Released Feb 12, 2026

    55/100
    • ECI145.8
    • Price$1.00 / $3.20
    • Context205K
    Full specs Remove GLM-5
01 — Verdict

Qwen3.5 397B-A17B is our pick

Qwen3.5 397B-A17B is the better all-round choice, scoring 65/100 against Qwen3.7 Max (58) and GLM-5 (55). It leads on price and inputs & features. Qwen3.7 Max wins on capability and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3.7 MaxCapabilities Index (ECI): Qwen3.7 Max 153.7 · Qwen3.5 397B-A17B 146.7 · GLM-5 145.8
  • Lowest priceQwen3.5 397B-A17BQwen3.5 397B-A17B $1.35 · GLM-5 $1.55 · Qwen3.7 Max $3.75 per 1M tokens (3:1 blend)
  • Longest contextQwen3.7 MaxQwen3.7 Max 1,000,000 · Qwen3.5 397B-A17B 262,144 · GLM-5 204,800 tokens
  • Widest inputsQwen3.5 397B-A17BQwen3.5 397B-A17B: Text, Images, Audio, Video · Qwen3.7 Max: Text · GLM-5: Text
  • Self-hostingQwen3.5 397B-A17B and GLM-5Publishes downloadable weights
How the score is built
MeasureWeightQwen3.5 397B-A17BQwen3.7 MaxGLM-5
CapabilityCapabilities Index (ECI)50%748373
Price25%442341
Inputs & features15%903535
Context window10%376032
Overall100%65/10058/10055/100
02 — Side by side

Every spec in one table

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

Qwen3.5 397B-A17B vs Qwen3.7 Max vs GLM-5 specifications side by side
SpecificationQwen3.5 397B-A17BAlibaba (Qwen)Qwen3.7 MaxAlibaba (Qwen)GLM-5Z.ai (Zhipu)
Capability
Capabilities Index (ECI)146.7153.7 (best)145.8
ECI rank#67 of 148#37 of 148 (best)#74 of 148
GPQA DiamondGraduate-level science questions86.4%90.9% (best)87.8%
FrontierMath Tiers 1–3Research-level mathematics31.2%64.6% (best)—
OTIS Mock AIME 2024–2025Competition mathematics88.9%95.6% (best)80.0%
SWE-bench VerifiedFixing real GitHub issues—77.3% (best)72.1%
SimpleQA VerifiedShort factual questions—55.8%—
Price per million tokens
Input$0.60 (best)$2.50$1.00
Output$3.60$7.50$3.20 (best)
Cached input—$0.50$0.20 (best)
Blended (3:1)$1.35 (best)$3.75$1.55
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial Alibaba APIOfficial Z.AI API
Limits
Context window262,144 tokens1,000,000 tokens (best)204,800 tokens
Max output65,536 tokens65,536 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenProprietaryOpen
API model IDqwen3.5-397b-a17bqwen3.7-maxglm-5
API providers232627 (best)
ReleasedFeb 15, 2026May 21, 2026Feb 12, 2026
Knowledge cutoff———
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.

  • Qwen3.5 397B-A17B$13.20
  • Qwen3.7 Max$40.00
  • GLM-5$16.40
04 — Questions

Which should you choose?

Which is better: Qwen3.5 397B-A17B, Qwen3.7 Max or GLM-5?

Qwen3.5 397B-A17B is the better all-round choice, scoring 65/100 against Qwen3.7 Max (58) and GLM-5 (55). It leads on price and inputs & features. Qwen3.7 Max wins on capability and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3.5 397B-A17B, Qwen3.7 Max or GLM-5?

Qwen3.5 397B-A17B is cheaper at $0.60 input / $3.60 output per million tokens (official Alibaba API price). GLM-5 costs $1.00 input / $3.20 output per million tokens (official Z.AI API price); Qwen3.7 Max costs $2.50 input / $7.50 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 $1.55 for GLM-5 (1.1× as much) and $3.75 for Qwen3.7 Max (2.8× as much).

Which scores higher on benchmarks?

Qwen3.7 Max scores higher on the Capabilities Index (ECI): Qwen3.7 Max 153.7 (#37 of 148), Qwen3.5 397B-A17B 146.7 (#67 of 148) and GLM-5 145.8 (#74 of 148). Their confidence ranges do not overlap (151.9–156.0 vs 144.8–148.2), so the gap is a real one. On individual benchmarks: GPQA Diamond — Qwen3.7 Max 90.9%, GLM-5 87.8%, Qwen3.5 397B-A17B 86.4%; OTIS Mock AIME 2024–2025 — Qwen3.7 Max 95.6%, Qwen3.5 397B-A17B 88.9%, GLM-5 80.0%.

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, Qwen3.7 Max 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?

Qwen3.7 Max has the largest context window at 1,000,000 tokens, against 262,144 for Qwen3.5 397B-A17B and 204,800 for GLM-5. Maximum output per response: Qwen3.5 397B-A17B up to 65,536, Qwen3.7 Max up to 65,536, GLM-5 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Qwen3.5 397B-A17B accepts text, images, audio and video; Qwen3.7 Max accepts text; GLM-5 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 publishes its weights and can be self-hosted; Qwen3.7 Max is proprietary.

Which is newer?

Qwen3.7 Max is the newest, released May 21, 2026. Qwen3.5 397B-A17B came out Feb 15, 2026; GLM-5 came out Feb 12, 2026.

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