ZMIME
Comparison · 3 models · Updated Oct 4, 2026

GLM-4.7 vs Kimi K2 Thinking vs Qwen3.6 27B

Qwen3.6 27B comes out ahead, 65 to 58 and 56 on our weighted score, though GLM-4.7 is 26% cheaper per token.

  1. Z.ai (Zhipu)

    GLM-4.7

    Released Dec 22, 2025

    56/100
    • ECI143.5
    • Price$0.60 / $2.20
    • Context205K
    Full specs Remove GLM-4.7

  2. Moonshot AI

    Kimi K2 Thinking

    Released Nov 6, 2025

    58/100
    • ECI146.0
    • Price$0.60 / $2.50
    • Context262K
    Full specs Remove Kimi K2 Thinking
  3. Our pick

    Alibaba (Qwen)

    Qwen3.6 27B

    Released Apr 22, 2026

    65/100
    • ECI146.5
    • Price$0.60 / $3.60
    • Context262K
    Full specs Remove Qwen3.6 27B
01 — Verdict

Qwen3.6 27B is our pick

Qwen3.6 27B is the better all-round choice, scoring 65/100 against Kimi K2 Thinking (58) and GLM-4.7 (56). It leads on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3.6 27BCapabilities Index (ECI): Qwen3.6 27B 146.5 · Kimi K2 Thinking 146.0 · GLM-4.7 143.5
  • Lowest priceGLM-4.7GLM-4.7 $1.00 · Kimi K2 Thinking $1.07 · Qwen3.6 27B $1.35 per 1M tokens (3:1 blend)
  • Longest contextKimi K2 Thinking and Qwen3.6 27BKimi K2 Thinking 262,144 · Qwen3.6 27B 262,144 · GLM-4.7 204,800 tokens
  • Widest inputsQwen3.6 27BGLM-4.7: Text · Kimi K2 Thinking: Text · Qwen3.6 27B: Text, Images, Audio, Video
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGLM-4.7Kimi K2 ThinkingQwen3.6 27B
CapabilityCapabilities Index (ECI)50%707374
Price25%504844
Inputs & features15%353590
Context window10%323737
Overall100%56/10058/10065/100
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 Kimi K2 Thinking vs Qwen3.6 27B specifications side by side
SpecificationGLM-4.7Z.ai (Zhipu)Kimi K2 ThinkingMoonshot AIQwen3.6 27BAlibaba (Qwen)
Capability
Capabilities Index (ECI)143.5146.0146.5 (best)
ECI rank#84 of 148#72 of 148#68 of 148 (best)
GPQA DiamondGraduate-level science questions83.3%84.2%85.9% (best)
FrontierMath Tiers 1–3Research-level mathematics——35.1%
OTIS Mock AIME 2024–2025Competition mathematics83.3%83.1%91.1% (best)
SimpleQA VerifiedShort factual questions32.2%——
Price per million tokens
Input$0.60$0.60$0.60
Output$2.20 (best)$2.50$3.60
Cached input$0.11——
Blended (3:1)$1.00 (best)$1.07$1.35
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIMedian of 10 providersOfficial Alibaba API
Limits
Context window204,800 tokens262,144 tokens (best)262,144 tokens (best)
Max output131,072 tokens262,144 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoYes
VideoNoNoYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenOpenOpen
API model IDglm-4.7—qwen3.6-27b
API providers201027 (best)
ReleasedDec 22, 2025Nov 6, 2025Apr 22, 2026
Knowledge cutoffApr 2025Aug 2024—
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
  • Kimi K2 Thinking$11.00
  • Qwen3.6 27B$13.20
04 — Questions

Which should you choose?

Which is better: GLM-4.7, Kimi K2 Thinking or Qwen3.6 27B?

Qwen3.6 27B is the better all-round choice, scoring 65/100 against Kimi K2 Thinking (58) and GLM-4.7 (56). It leads on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GLM-4.7, Kimi K2 Thinking or Qwen3.6 27B?

GLM-4.7 is cheaper at $0.60 input / $2.20 output per million tokens (official Z.AI API price). Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 10 API providers); Qwen3.6 27B costs $0.60 input / $3.60 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for GLM-4.7 versus $1.07 for Kimi K2 Thinking (1.1× as much) and $1.35 for Qwen3.6 27B (1.4× as much).

Which scores higher on benchmarks?

Qwen3.6 27B scores higher on the Capabilities Index (ECI): Qwen3.6 27B 146.5 (#68 of 148), Kimi K2 Thinking 146.0 (#72 of 148) and GLM-4.7 143.5 (#84 of 148). The confidence ranges of the top two overlap (144.2–147.9 vs 143.4–147.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.6 27B 85.9%, Kimi K2 Thinking 84.2%, GLM-4.7 83.3%; OTIS Mock AIME 2024–2025 — Qwen3.6 27B 91.1%, GLM-4.7 83.3%, Kimi K2 Thinking 83.1%.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.7, Kimi K2 Thinking and Qwen3.6 27B yet, so there is no like-for-like coding score. On overall capability, Qwen3.6 27B 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?

Kimi K2 Thinking and Qwen3.6 27B have the largest context windows (262,144 and 262,144 tokens), against 204,800 for GLM-4.7. Maximum output per response: GLM-4.7 up to 131,072, Kimi K2 Thinking up to 262,144, Qwen3.6 27B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GLM-4.7 accepts text; Kimi K2 Thinking accepts text; Qwen3.6 27B accepts text, images, audio and video. Qwen3.6 27B handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

Qwen3.6 27B is the newest, released Apr 22, 2026. GLM-4.7 came out Dec 22, 2025; Kimi K2 Thinking came out Nov 6, 2025. Knowledge cutoff: GLM-4.7 Apr 2025, Kimi K2 Thinking Aug 2024.

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