ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GLM-4.7 vs Claude Haiku 4.5 vs QwQ 32B

Claude Haiku 4.5 comes out ahead, 68 to 60 and 54 on our weighted score, though QwQ 32B is 3.5× 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. Our pick

    Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    68/100
    • ECI142.8
    • Price$1.00 / $5.00
    • Context200K
  3. Alibaba (Qwen)

    QwQ 32B

    Released Mar 5, 2025

    54/100
    • ECI136.5
    • Price$0.53 / $0.70
    • Context131K
01 — Verdict

Claude Haiku 4.5 is our pick

Claude Haiku 4.5 is the better all-round choice, scoring 68/100 against GLM-4.7 (60) and QwQ 32B (54). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGLM-4.7Capabilities Index (ECI): GLM-4.7 143.4 · Claude Haiku 4.5 142.8 · QwQ 32B 136.5
  • Lowest priceQwQ 32BQwQ 32B $0.573 · GLM-4.7 $1.00 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
  • Longest contextGLM-4.7GLM-4.7 204,800 · Claude Haiku 4.5 200,000 · QwQ 32B 131,072 tokens
  • Widest inputsClaude Haiku 4.5GLM-4.7: Text · Claude Haiku 4.5: Text, Images, PDFs · QwQ 32B: Text
  • Self-hostingGLM-4.7 and QwQ 32BPublishes downloadable weights
How the score is built
MeasureWeightGLM-4.7Claude Haiku 4.5QwQ 32B
CapabilityCapabilities Index (ECI)67%717065
Inputs & features20%358035
Context window13%393932
Overall100%60/10068/10054/100
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 QwQ 32B specifications side by side
SpecificationGLM-4.7Z.ai (Zhipu)Claude Haiku 4.5AnthropicQwQ 32BAlibaba (Qwen)
Capability
Capabilities Index (ECI)143.4 (best)142.8136.5
ECI rank#99 of 158 (best)#102 of 158#122 of 158
GPQA DiamondGraduate-level science questions83.3% (best)71.2%65.3%
OTIS Mock AIME 2024–2025Competition mathematics83.3% (best)66.7%59.2%
SimpleQA VerifiedShort factual questions32.2% (best)13.2%—
Price per million tokens
Input$0.60$1.00$0.53 (best)
Output$2.20$5.00$0.70 (best)
Cached input$0.11$0.10 (best)—
Blended (3:1)$1.00$2.00$0.573 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIOfficial Anthropic APIMedian of 2 providers
Limits
Context window204,800 tokens (best)200,000 tokens131,072 tokens
Max output131,072 tokens (best)64,000 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryOpen
API model IDglm-4.7claude-haiku-4-5—
API providers3057 (best)2
ReleasedDec 22, 2025Oct 15, 2025Mar 5, 2025
Knowledge cutoffApr 2025Feb 28, 2025Apr 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
  • Claude Haiku 4.5$20.00
  • QwQ 32B$6.70
04 — Questions

Which should you choose?

Which is better: GLM-4.7, Claude Haiku 4.5 or QwQ 32B?

Claude Haiku 4.5 is the better all-round choice, scoring 68/100 against GLM-4.7 (60) and QwQ 32B (54). It leads 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 QwQ 32B?

QwQ 32B is cheaper at $0.53 input / $0.70 output per million tokens (median across 2 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 $0.573 per million tokens for QwQ 32B versus $1.00 for GLM-4.7 (1.7× as much) and $2.00 for Claude Haiku 4.5 (3.5× as much).

Which scores higher on benchmarks?

GLM-4.7 scores higher on the Capabilities Index (ECI): GLM-4.7 143.4 (#99 of 158), Claude Haiku 4.5 142.8 (#102 of 158) and QwQ 32B 136.5 (#122 of 158). The confidence ranges of the top two overlap (141.4–145.3 vs 141.2–144.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-4.7 83.3%, Claude Haiku 4.5 71.2%, QwQ 32B 65.3%; OTIS Mock AIME 2024–2025 — GLM-4.7 83.3%, Claude Haiku 4.5 66.7%, QwQ 32B 59.2%.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.7, Claude Haiku 4.5 and QwQ 32B 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?

GLM-4.7 has the largest context window at 204,800 tokens, against 200,000 for Claude Haiku 4.5 and 131,072 for QwQ 32B. Maximum output per response: GLM-4.7 up to 131,072, Claude Haiku 4.5 up to 64,000, QwQ 32B up to 8,192 tokens.

Which can read images, PDFs, audio or video?

GLM-4.7 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; QwQ 32B accepts text. Claude Haiku 4.5 handles the widest range of inputs.

Are any of these open source?

GLM-4.7 and QwQ 32B publishes its weights 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; QwQ 32B came out Mar 5, 2025. Knowledge cutoff: GLM-4.7 Apr 2025, Claude Haiku 4.5 Feb 28, 2025, QwQ 32B Apr 2024.

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.