ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GLM-4.7 vs GLM-5 vs Qwen3 235B-A22B Thinking 2507

Too close to call on our weighted score (GLM-5 62, Qwen3 235B-A22B Thinking 2507 60, GLM-4.7 60). The right pick depends on what you value most.

Price in rating: Excluded · Include price

  1. Z.ai (Zhipu)

    GLM-4.7

    Released Dec 22, 2025

    60/100
    • ECI143.4
    • Price$0.60 / $2.20
    • Context205K
  2. Z.ai (Zhipu)

    GLM-5

    Released Feb 12, 2026

    62/100
    • ECI146.5
    • Price$1.00 / $3.20
    • Context205K
  3. Alibaba (Qwen)

    Qwen3 235B-A22B Thinking 2507

    Released Jul 25, 2025

    60/100
    • ECI143.3
    • Price$0.30 / $2.90
    • Context262K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (GLM-5 62/100, Qwen3 235B-A22B Thinking 2507 60/100, GLM-4.7 60/100), so choose by what matters most for your work: GLM-5 for raw capability, Qwen3 235B-A22B Thinking 2507 on price and Qwen3 235B-A22B Thinking 2507 for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGLM-5Capabilities Index (ECI): GLM-5 146.5 · GLM-4.7 143.4 · Qwen3 235B-A22B Thinking 2507 143.3
  • Lowest priceQwen3 235B-A22B Thinking 2507Qwen3 235B-A22B Thinking 2507 $0.95 · GLM-4.7 $1.00 · GLM-5 $1.55 per 1M tokens (3:1 blend)
  • Longest contextQwen3 235B-A22B Thinking 2507Qwen3 235B-A22B Thinking 2507 262,144 · GLM-4.7 204,800 · GLM-5 204,800 tokens
  • Widest inputsSame inputsGLM-4.7: Text · GLM-5: Text · Qwen3 235B-A22B Thinking 2507: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGLM-4.7GLM-5Qwen3 235B-A22B Thinking 2507
CapabilityCapabilities Index (ECI)67%717471
Inputs & features20%353535
Context window13%393943
Overall100%60/10062/10060/100
02 — Side by side

Every spec in one table

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

GLM-4.7 vs GLM-5 vs Qwen3 235B-A22B Thinking 2507 specifications side by side
SpecificationGLM-4.7Z.ai (Zhipu)GLM-5Z.ai (Zhipu)Qwen3 235B-A22B Thinking 2507Alibaba (Qwen)
Capability
Capabilities Index (ECI)143.4146.5 (best)143.3
ECI rank#99 of 158#85 of 158 (best)#100 of 158
GPQA DiamondGraduate-level science questions83.3%87.8% (best)80.1%
OTIS Mock AIME 2024–2025Competition mathematics83.3%80.0%86.7% (best)
SWE-bench VerifiedFixing real GitHub issues—72.1%—
SimpleQA VerifiedShort factual questions32.2%—40.4% (best)
Price per million tokens
Input$0.60$1.00$0.30 (best)
Output$2.20 (best)$3.20$2.90
Cached input$0.11 (best)$0.20—
Blended (3:1)$1.00$1.55$0.95 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIOfficial Z.AI APIMedian of 11 providers
Limits
Context window204,800 tokens204,800 tokens262,144 tokens (best)
Max output131,072 tokens (best)131,072 tokens (best)81,920 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpenApache 2.0
API model IDglm-4.7glm-5—
API providers3037 (best)12
ReleasedDec 22, 2025Feb 12, 2026Jul 25, 2025
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.

  • GLM-4.7$10.40
  • GLM-5$16.40
  • Qwen3 235B-A22B Thinking 2507$8.80
04 — Questions

Which should you choose?

Which is better: GLM-4.7, GLM-5 or Qwen3 235B-A22B Thinking 2507?

It is close. Our weighted score puts them within 2 points (GLM-5 62/100, Qwen3 235B-A22B Thinking 2507 60/100, GLM-4.7 60/100), so choose by what matters most for your work: GLM-5 for raw capability, Qwen3 235B-A22B Thinking 2507 on price and Qwen3 235B-A22B Thinking 2507 for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, GLM-4.7, GLM-5 or Qwen3 235B-A22B Thinking 2507?

Qwen3 235B-A22B Thinking 2507 is cheaper at $0.30 input / $2.90 output per million tokens (median across 11 API providers). GLM-4.7 costs $0.60 input / $2.20 output per million tokens (official Z.AI API price); GLM-5 costs $1.00 input / $3.20 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.95 per million tokens for Qwen3 235B-A22B Thinking 2507 versus $1.00 for GLM-4.7 (1.1× as much) and $1.55 for GLM-5 (1.6× as much).

Which scores higher on benchmarks?

GLM-5 scores higher on the Capabilities Index (ECI): GLM-5 146.5 (#85 of 158), GLM-4.7 143.4 (#99 of 158) and Qwen3 235B-A22B Thinking 2507 143.3 (#100 of 158). The confidence ranges of the top two overlap (145.0–148.1 vs 141.4–145.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5 87.8%, GLM-4.7 83.3%, Qwen3 235B-A22B Thinking 2507 80.1%; OTIS Mock AIME 2024–2025 — Qwen3 235B-A22B Thinking 2507 86.7%, GLM-4.7 83.3%, GLM-5 80.0%.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.7 and Qwen3 235B-A22B Thinking 2507 yet, so there is no like-for-like coding score. On overall capability, GLM-5 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 235B-A22B Thinking 2507 has the largest context window at 262,144 tokens, against 204,800 for GLM-4.7 and 204,800 for GLM-5. Maximum output per response: GLM-4.7 up to 131,072, GLM-5 up to 131,072, Qwen3 235B-A22B Thinking 2507 up to 81,920 tokens.

Which can read images, PDFs, audio or video?

GLM-4.7 accepts text; GLM-5 accepts text; Qwen3 235B-A22B Thinking 2507 accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights (Apache 2.0), so you can self-host them.

Which is newer?

GLM-5 is the newest, released Feb 12, 2026. GLM-4.7 came out Dec 22, 2025; Qwen3 235B-A22B Thinking 2507 came out Jul 25, 2025. Knowledge cutoff: GLM-4.7 Apr 2025.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 Nov 18, 2026.