ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GLM-4.7 vs Claude Haiku 4.5 vs Inkling

Inkling comes out ahead, 73 to 68 and 60 on our weighted score, though GLM-4.7 is 2.6× cheaper per token.

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. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    68/100
    • ECI142.8
    • Price$1.00 / $5.00
    • Context200K
  3. Our pick

    Thinking Machines

    Inkling

    Released Jul 15, 2026

    73/100
    • ECI148.4
    • Price$1.87 / $4.68
    • Context1.05M
01 — Verdict

Inkling is our pick

Inkling is the better all-round choice, scoring 73/100 against Claude Haiku 4.5 (68) and GLM-4.7 (60). It leads on capability and context window. Claude Haiku 4.5 wins on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityInklingCapabilities Index (ECI): Inkling 148.4 · GLM-4.7 143.4 · Claude Haiku 4.5 142.8
  • Lowest priceGLM-4.7GLM-4.7 $1.00 · Claude Haiku 4.5 $2.00 · Inkling $2.57 per 1M tokens (3:1 blend)
  • Longest contextInklingInkling 1,048,576 · GLM-4.7 204,800 · Claude Haiku 4.5 200,000 tokens
  • Widest inputsClaude Haiku 4.5 and InklingGLM-4.7: Text · Claude Haiku 4.5: Text, Images, PDFs · Inkling: Text, Images, Audio
  • Self-hostingGLM-4.7 and InklingPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightGLM-4.7Claude Haiku 4.5Inkling
CapabilityCapabilities Index (ECI)67%717076
Inputs & features20%358070
Context window13%393965
Overall100%60/10068/10073/100
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 Claude Haiku 4.5 vs Inkling specifications side by side
SpecificationGLM-4.7Z.ai (Zhipu)Claude Haiku 4.5AnthropicInklingThinking Machines
Capability
Capabilities Index (ECI)143.4142.8148.4 (best)
ECI rank#99 of 158#102 of 158#74 of 158 (best)
GPQA DiamondGraduate-level science questions83.3%71.2%88.3% (best)
FrontierMath Tiers 1–3Research-level mathematics——33.3%
OTIS Mock AIME 2024–2025Competition mathematics83.3%66.7%88.9% (best)
SimpleQA VerifiedShort factual questions32.2%13.2%40.3% (best)
Price per million tokens
Input$0.60 (best)$1.00$1.87
Output$2.20 (best)$5.00$4.68
Cached input$0.11$0.10 (best)$0.374
Blended (3:1)$1.00 (best)$2.00$2.57
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIOfficial Anthropic APIOfficial Thinking Machines API
Limits
Context window204,800 tokens200,000 tokens1,048,576 tokens (best)
Max output131,072 tokens64,000 tokens1,048,576 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoYes
VideoNoNoNo
ReasoningYesYesYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryOpenApache-2.0
API model IDglm-4.7claude-haiku-4-5thinkingmachines/Inkling
API providers3057 (best)18
ReleasedDec 22, 2025Oct 15, 2025Jul 15, 2026
Knowledge cutoffApr 2025Feb 28, 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
  • Claude Haiku 4.5$20.00
  • Inkling$28.06
04 — Questions

Which should you choose?

Which is better: GLM-4.7, Claude Haiku 4.5 or Inkling?

Inkling is the better all-round choice, scoring 73/100 against Claude Haiku 4.5 (68) and GLM-4.7 (60). It leads on capability and context window. Claude Haiku 4.5 wins on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, GLM-4.7, Claude Haiku 4.5 or Inkling?

GLM-4.7 is cheaper at $0.60 input / $2.20 output per million tokens (official Z.AI API price). Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price); Inkling costs $1.87 input / $4.68 output per million tokens (official Thinking Machines 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 $2.00 for Claude Haiku 4.5 (2× as much) and $2.57 for Inkling (2.6× as much).

Which scores higher on benchmarks?

Inkling scores higher on the Capabilities Index (ECI): Inkling 148.4 (#74 of 158), GLM-4.7 143.4 (#99 of 158) and Claude Haiku 4.5 142.8 (#102 of 158). Their confidence ranges do not overlap (146.9–150.0 vs 141.4–145.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — Inkling 88.3%, GLM-4.7 83.3%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Inkling 88.9%, GLM-4.7 83.3%, Claude Haiku 4.5 66.7%; SimpleQA Verified — Inkling 40.3%, GLM-4.7 32.2%, Claude Haiku 4.5 13.2%.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.7, Claude Haiku 4.5 and Inkling yet, so there is no like-for-like coding score. On overall capability, Inkling 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?

Inkling has the largest context window at 1,048,576 tokens, against 204,800 for GLM-4.7 and 200,000 for Claude Haiku 4.5. Maximum output per response: GLM-4.7 up to 131,072, Claude Haiku 4.5 up to 64,000, Inkling up to 1,048,576 tokens.

Which can read images, PDFs, audio or video?

GLM-4.7 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; Inkling accepts text, images and audio. Claude Haiku 4.5 handles the widest range of inputs.

Are any of these open source?

GLM-4.7 and Inkling publishes its weights (Apache-2.0) and can be self-hosted; Claude Haiku 4.5 is proprietary.

Which is newer?

Inkling is the newest, released Jul 15, 2026. GLM-4.7 came out Dec 22, 2025; Claude Haiku 4.5 came out Oct 15, 2025. Knowledge cutoff: GLM-4.7 Apr 2025, Claude Haiku 4.5 Feb 28, 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.