ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Claude Haiku 4.5 vs Qwen3 VL 30B A3B Instruct vs GLM-4.7

Qwen3 VL 30B A3B Instruct comes out ahead, 62 to 47 and 41 on our weighted score, and it is the cheaper option too.

  1. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    47/100
    • ECI142.2
    • Price$1.00 / $5.00
    • Context200K
    Full specs Remove Claude Haiku 4.5
  2. Our pick

    Alibaba (Qwen)

    Qwen3 VL 30B A3B Instruct

    Released Oct 4, 2025

    62/100
    • ECI—
    • Price$0.15 / $0.60
    • Context262K
    Full specs Remove Qwen3 VL 30B A3B Instruct

  3. Z.ai (Zhipu)

    GLM-4.7

    Released Dec 22, 2025

    41/100
    • ECI143.7
    • Price$0.60 / $2.20
    • Context205K
    Full specs Remove GLM-4.7
01 — Verdict

Qwen3 VL 30B A3B Instruct is our pick

Qwen3 VL 30B A3B Instruct is the better all-round choice, scoring 62/100 against Claude Haiku 4.5 (47) and GLM-4.7 (41). It leads on price and context window. Claude Haiku 4.5 wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceQwen3 VL 30B A3B InstructQwen3 VL 30B A3B Instruct $0.263 · GLM-4.7 $1.00 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
  • Longest contextQwen3 VL 30B A3B InstructQwen3 VL 30B A3B Instruct 262,144 · GLM-4.7 204,800 · Claude Haiku 4.5 200,000 tokens
  • Widest inputsClaude Haiku 4.5 and Qwen3 VL 30B A3B InstructClaude Haiku 4.5: Text, Images, PDFs · Qwen3 VL 30B A3B Instruct: Text, Images, Video · GLM-4.7: Text
  • Self-hostingQwen3 VL 30B A3B Instruct and GLM-4.7Publishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightClaude Haiku 4.5Qwen3 VL 30B A3B InstructGLM-4.7
Price50%347448
Inputs & features30%806035
Context window20%323732
Overall100%47/10062/10041/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

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 Qwen3 VL 30B A3B Instruct vs GLM-4.7 specifications side by side
SpecificationClaude Haiku 4.5AnthropicQwen3 VL 30B A3B InstructAlibaba (Qwen)GLM-4.7Z.ai (Zhipu)
Capability
Capabilities Index (ECI)142.2—143.7 (best)
ECI rank#102 of 165—#94 of 165 (best)
GPQA DiamondGraduate-level science questions71.2%—83.3% (best)
OTIS Mock AIME 2024–2025Competition mathematics66.7%—83.3% (best)
SimpleQA VerifiedShort factual questions13.2%—32.2% (best)
Price per million tokens
Input$1.00$0.15 (best)$0.60
Output$5.00$0.60 (best)$2.20
Cached input$0.10 (best)—$0.11
Blended (3:1)$2.00$0.263 (best)$1.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Anthropic APIMedian of 13 providersOfficial Z.AI API
Limits
Context window200,000 tokens262,144 tokens (best)204,800 tokens
Max output64,000 tokens32,768 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesNoNo
AudioNoNoNo
VideoNoYesNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenApache-2.0Open
API model IDclaude-haiku-4-5—glm-4.7
API providers48 (best)1331
ReleasedOct 15, 2025Oct 4, 2025Dec 22, 2025
Knowledge cutoffFeb 28, 2025—Apr 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
  • Qwen3 VL 30B A3B Instruct$2.70
  • GLM-4.7$10.40
04 — Questions

Which should you choose?

Which is better: Claude Haiku 4.5, Qwen3 VL 30B A3B Instruct or GLM-4.7?

Qwen3 VL 30B A3B Instruct is the better all-round choice, scoring 62/100 against Claude Haiku 4.5 (47) and GLM-4.7 (41). It leads on price and context window. Claude Haiku 4.5 wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Claude Haiku 4.5, Qwen3 VL 30B A3B Instruct or GLM-4.7?

Qwen3 VL 30B A3B Instruct is cheaper at $0.15 input / $0.60 output per million tokens (median across 13 API providers). 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 $0.263 per million tokens for Qwen3 VL 30B A3B Instruct versus $1.00 for GLM-4.7 (3.8× as much) and $2.00 for Claude Haiku 4.5 (7.6× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Claude Haiku 4.5 has an ECI of 142.2, Qwen3 VL 30B A3B Instruct has not been scored yet and GLM-4.7 has an ECI of 143.7.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 4.5, Qwen3 VL 30B A3B Instruct and GLM-4.7 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Qwen3 VL 30B A3B Instruct has the largest context window at 262,144 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, Qwen3 VL 30B A3B Instruct up to 32,768, 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; Qwen3 VL 30B A3B Instruct accepts text, images and video; GLM-4.7 accepts text. Claude Haiku 4.5 handles the widest range of inputs.

Are any of these open source?

Qwen3 VL 30B A3B Instruct and GLM-4.7 publishes its weights (Apache-2.0) and can be self-hosted; Claude Haiku 4.5 is proprietary.

Which is newer?

GLM-4.7 is the newest, released Dec 22, 2025. Claude Haiku 4.5 came out Oct 15, 2025; Qwen3 VL 30B A3B Instruct came out Oct 4, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, 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