ZMIME
Comparison · 3 models · Updated Oct 4, 2026

GLM-4.7 vs Qwen3.5 35B-A3B vs Kimi K2 Thinking

Qwen3.5 35B-A3B comes out ahead, 66 to 58 and 56 on our weighted score, and it is the cheaper option too.

  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. Our pick

    Alibaba (Qwen)

    Qwen3.5 35B-A3B

    Released Feb 23, 2026

    66/100
    • ECI142.5
    • Price$0.25 / $2.00
    • Context262K
    Full specs Remove Qwen3.5 35B-A3B

  3. 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
01 — Verdict

Qwen3.5 35B-A3B is our pick

Qwen3.5 35B-A3B is the better all-round choice, scoring 66/100 against Kimi K2 Thinking (58) and GLM-4.7 (56). It leads on price and inputs & features. Kimi K2 Thinking wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityKimi K2 ThinkingCapabilities Index (ECI): Kimi K2 Thinking 146.0 · GLM-4.7 143.5 · Qwen3.5 35B-A3B 142.5
  • Lowest priceQwen3.5 35B-A3BQwen3.5 35B-A3B $0.688 · GLM-4.7 $1.00 · Kimi K2 Thinking $1.07 per 1M tokens (3:1 blend)
  • Longest contextQwen3.5 35B-A3B and Kimi K2 ThinkingQwen3.5 35B-A3B 262,144 · Kimi K2 Thinking 262,144 · GLM-4.7 204,800 tokens
  • Widest inputsQwen3.5 35B-A3BGLM-4.7: Text · Qwen3.5 35B-A3B: Text, Images, Audio, Video · Kimi K2 Thinking: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGLM-4.7Qwen3.5 35B-A3BKimi K2 Thinking
CapabilityCapabilities Index (ECI)50%706973
Price25%505848
Inputs & features15%359035
Context window10%323737
Overall100%56/10066/10058/100
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 Qwen3.5 35B-A3B vs Kimi K2 Thinking specifications side by side
SpecificationGLM-4.7Z.ai (Zhipu)Qwen3.5 35B-A3BAlibaba (Qwen)Kimi K2 ThinkingMoonshot AI
Capability
Capabilities Index (ECI)143.5142.5146.0 (best)
ECI rank#84 of 148#88 of 148#72 of 148 (best)
GPQA DiamondGraduate-level science questions83.3%83.5%84.2% (best)
OTIS Mock AIME 2024–2025Competition mathematics83.3% (best)70.0%83.1%
SimpleQA VerifiedShort factual questions32.2%——
Price per million tokens
Input$0.60$0.25 (best)$0.60
Output$2.20$2.00 (best)$2.50
Cached input$0.11——
Blended (3:1)$1.00$0.688 (best)$1.07
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIOfficial Alibaba APIMedian of 10 providers
Limits
Context window204,800 tokens262,144 tokens (best)262,144 tokens (best)
Max output131,072 tokens65,536 tokens262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoYesNo
VideoNoYesNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenOpenOpen
API model IDglm-4.7qwen3.5-35b-a3b—
API providers20 (best)1810
ReleasedDec 22, 2025Feb 23, 2026Nov 6, 2025
Knowledge cutoffApr 2025—Aug 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
  • Qwen3.5 35B-A3B$6.50
  • Kimi K2 Thinking$11.00
04 — Questions

Which should you choose?

Which is better: GLM-4.7, Qwen3.5 35B-A3B or Kimi K2 Thinking?

Qwen3.5 35B-A3B is the better all-round choice, scoring 66/100 against Kimi K2 Thinking (58) and GLM-4.7 (56). It leads on price and inputs & features. Kimi K2 Thinking wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GLM-4.7, Qwen3.5 35B-A3B or Kimi K2 Thinking?

Qwen3.5 35B-A3B is cheaper at $0.25 input / $2.00 output per million tokens (official Alibaba API price). GLM-4.7 costs $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). At a typical mix of three input tokens to one output token, that is $0.688 per million tokens for Qwen3.5 35B-A3B versus $1.00 for GLM-4.7 (1.5× as much) and $1.07 for Kimi K2 Thinking (1.6× as much).

Which scores higher on benchmarks?

Kimi K2 Thinking scores higher on the Capabilities Index (ECI): Kimi K2 Thinking 146.0 (#72 of 148), GLM-4.7 143.5 (#84 of 148) and Qwen3.5 35B-A3B 142.5 (#88 of 148). The confidence ranges of the top two overlap (143.4–147.6 vs 141.3–145.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2 Thinking 84.2%, Qwen3.5 35B-A3B 83.5%, GLM-4.7 83.3%; OTIS Mock AIME 2024–2025 — GLM-4.7 83.3%, Kimi K2 Thinking 83.1%, Qwen3.5 35B-A3B 70.0%.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.7, Qwen3.5 35B-A3B and Kimi K2 Thinking yet, so there is no like-for-like coding score. On overall capability, Kimi K2 Thinking 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?

Qwen3.5 35B-A3B and Kimi K2 Thinking 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, Qwen3.5 35B-A3B up to 65,536, Kimi K2 Thinking up to 262,144 tokens.

Which can read images, PDFs, audio or video?

GLM-4.7 accepts text; Qwen3.5 35B-A3B accepts text, images, audio and video; Kimi K2 Thinking accepts text. Qwen3.5 35B-A3B 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?

Qwen3.5 35B-A3B is the newest, released Feb 23, 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