ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Claude Haiku 4.5 vs GPT-5 Nano vs GLM-4.7

GPT-5 Nano comes out ahead, 68 to 57 and 55 on our weighted score, and it is the cheaper option too.

  1. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    57/100
    • ECI142.2
    • Price$1.00 / $5.00
    • Context200K
    Full specs Remove Claude Haiku 4.5
  2. Our pick

    OpenAI

    GPT-5 Nano

    Released Aug 7, 2025

    68/100
    • ECI139.3
    • Price$0.05 / $0.40
    • Context400K
    Full specs Remove GPT-5 Nano

  3. Z.ai (Zhipu)

    GLM-4.7

    Released Dec 22, 2025

    55/100
    • ECI143.7
    • Price$0.60 / $2.20
    • Context205K
    Full specs Remove GLM-4.7
01 — Verdict

GPT-5 Nano is our pick

GPT-5 Nano is the better all-round choice, scoring 68/100 against Claude Haiku 4.5 (57) and GLM-4.7 (55). It leads on price and context window. Claude Haiku 4.5 wins on inputs & features. GLM-4.7 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGLM-4.7Capabilities Index (ECI): GLM-4.7 143.7 · Claude Haiku 4.5 142.2 · GPT-5 Nano 139.3
  • Lowest priceGPT-5 NanoGPT-5 Nano $0.138 · GLM-4.7 $1.00 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-5 NanoGPT-5 Nano 400,000 · GLM-4.7 204,800 · Claude Haiku 4.5 200,000 tokens
  • Widest inputsClaude Haiku 4.5Claude Haiku 4.5: Text, Images, PDFs · GPT-5 Nano: Text, Images · GLM-4.7: Text
  • Self-hostingGLM-4.7Publishes downloadable weights
How the score is built
MeasureWeightClaude Haiku 4.5GPT-5 NanoGLM-4.7
CapabilityCapabilities Index (ECI)50%676369
Price25%348748
Inputs & features15%807035
Context window10%324432
Overall100%57/10068/10055/100
02 — Side by side

Every spec in one table

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

Claude Haiku 4.5 vs GPT-5 Nano vs GLM-4.7 specifications side by side
SpecificationClaude Haiku 4.5AnthropicGPT-5 NanoOpenAIGLM-4.7Z.ai (Zhipu)
Capability
Capabilities Index (ECI)142.2139.3143.7 (best)
ECI rank#102 of 165#116 of 165#94 of 165 (best)
GPQA DiamondGraduate-level science questions71.2%69.4%83.3% (best)
FrontierMath Tiers 1–3Research-level mathematics—20.0%—
OTIS Mock AIME 2024–2025Competition mathematics66.7%81.1%83.3% (best)
SimpleQA VerifiedShort factual questions13.2%11.7%32.2% (best)
Price per million tokens
Input$1.00$0.05 (best)$0.60
Output$5.00$0.40 (best)$2.20
Cached input$0.10$0.005 (best)$0.11
Blended (3:1)$2.00$0.138 (best)$1.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Anthropic APIOfficial OpenAI APIOfficial Z.AI API
Limits
Context window200,000 tokens400,000 tokens (best)204,800 tokens
Max output64,000 tokens128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesminimal · low · medium · highYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpen
API model IDclaude-haiku-4-5gpt-5-nanoglm-4.7
API providers48 (best)3031
ReleasedOct 15, 2025Aug 7, 2025Dec 22, 2025
Knowledge cutoffFeb 28, 2025May 30, 2024Apr 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.

  • Claude Haiku 4.5$20.00
  • GPT-5 Nano$1.30
  • GLM-4.7$10.40
04 — Questions

Which should you choose?

Which is better: Claude Haiku 4.5, GPT-5 Nano or GLM-4.7?

GPT-5 Nano is the better all-round choice, scoring 68/100 against Claude Haiku 4.5 (57) and GLM-4.7 (55). It leads on price and context window. Claude Haiku 4.5 wins on inputs & features. GLM-4.7 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Haiku 4.5, GPT-5 Nano or GLM-4.7?

GPT-5 Nano is cheaper at $0.05 input / $0.40 output per million tokens (official OpenAI API price). GLM-4.7 costs $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). At a typical mix of three input tokens to one output token, that is $0.138 per million tokens for GPT-5 Nano versus $1.00 for GLM-4.7 (7.3× as much) and $2.00 for Claude Haiku 4.5 (15× as much).

Which scores higher on benchmarks?

GLM-4.7 scores higher on the Capabilities Index (ECI): GLM-4.7 143.7 (#94 of 165), Claude Haiku 4.5 142.2 (#102 of 165) and GPT-5 Nano 139.3 (#116 of 165). The confidence ranges of the top two overlap (141.4–145.8 vs 139.4–143.9), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-4.7 83.3%, Claude Haiku 4.5 71.2%, GPT-5 Nano 69.4%; OTIS Mock AIME 2024–2025 — GLM-4.7 83.3%, GPT-5 Nano 81.1%, Claude Haiku 4.5 66.7%; SimpleQA Verified — GLM-4.7 32.2%, Claude Haiku 4.5 13.2%, GPT-5 Nano 11.7%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 4.5, GPT-5 Nano and GLM-4.7 yet, so there is no like-for-like coding score. On overall capability, GLM-4.7 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?

GPT-5 Nano has the largest context window at 400,000 tokens, against 204,800 for GLM-4.7 and 200,000 for Claude Haiku 4.5. Maximum output per response: Claude Haiku 4.5 up to 64,000, GPT-5 Nano up to 128,000, GLM-4.7 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 4.5 accepts text, images and PDFs; GPT-5 Nano accepts text and images; GLM-4.7 accepts text. Claude Haiku 4.5 handles the widest range of inputs.

Are any of these open source?

GLM-4.7 publishes its weights and can be self-hosted; Claude Haiku 4.5 and GPT-5 Nano is proprietary.

Which is newer?

GLM-4.7 is the newest, released Dec 22, 2025. Claude Haiku 4.5 came out Oct 15, 2025; GPT-5 Nano came out Aug 7, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, GPT-5 Nano May 30, 2024, GLM-4.7 Apr 2025.

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 Nov 2, 2026.

05 — Keep comparing

Related comparisons