ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek-R1 vs GLM-4.7 vs Claude Haiku 4.5

Too close to call on our weighted score (Claude Haiku 4.5 60, GLM-4.7 57, DeepSeek-R1 50). The right pick depends on what you value most.

Price in rating: Included · Exclude price

  1. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    50/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
  2. Z.ai (Zhipu)

    GLM-4.7

    Released Dec 22, 2025

    57/100
    • ECI143.4
    • Price$0.60 / $2.20
    • Context205K
  3. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    60/100
    • ECI142.8
    • Price$1.00 / $5.00
    • Context200K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 3 points (Claude Haiku 4.5 60/100, GLM-4.7 57/100, DeepSeek-R1 50/100), so choose by what matters most for your work: GLM-4.7 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGLM-4.7Capabilities Index (ECI): GLM-4.7 143.4 · Claude Haiku 4.5 142.8 · DeepSeek-R1 138.6
  • Lowest priceGLM-4.7GLM-4.7 $1.00 · Claude Haiku 4.5 $2.00 · DeepSeek-R1 $2.05 per 1M tokens (3:1 blend)
  • Longest contextGLM-4.7GLM-4.7 204,800 · Claude Haiku 4.5 200,000 · DeepSeek-R1 128,000 tokens
  • Widest inputsClaude Haiku 4.5DeepSeek-R1: Text · GLM-4.7: Text · Claude Haiku 4.5: Text, Images, PDFs
  • Self-hostingDeepSeek-R1 and GLM-4.7Publishes downloadable weights
How the score is built
MeasureWeightDeepSeek-R1GLM-4.7Claude Haiku 4.5
CapabilityCapabilities Index (ECI)50%677170
Price25%344834
Inputs & features15%353580
Context window10%323939
Overall100%50/10057/10060/100
02 — Side by side

Every spec in one table

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

DeepSeek-R1 vs GLM-4.7 vs Claude Haiku 4.5 specifications side by side
SpecificationDeepSeek-R1DeepSeekGLM-4.7Z.ai (Zhipu)Claude Haiku 4.5Anthropic
Capability
Capabilities Index (ECI)138.6143.4 (best)142.8
ECI rank#118 of 158#99 of 158 (best)#102 of 158
GPQA DiamondGraduate-level science questions71.7%83.3% (best)71.2%
OTIS Mock AIME 2024–2025Competition mathematics53.3%83.3% (best)66.7%
SimpleQA VerifiedShort factual questions—32.2% (best)13.2%
Price per million tokens
Input$1.02$0.60 (best)$1.00
Output$5.14$2.20 (best)$5.00
Cached input—$0.11$0.10 (best)
Blended (3:1)$2.05$1.00 (best)$2.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 12 providersOfficial Z.AI APIOfficial Anthropic API
Limits
Context window128,000 tokens204,800 tokens (best)200,000 tokens
Max output32,768 tokens131,072 tokens (best)64,000 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenOpenProprietary
API model ID—glm-4.7claude-haiku-4-5
API providers133057 (best)
ReleasedJan 20, 2025Dec 22, 2025Oct 15, 2025
Knowledge cutoffJul 2024Apr 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.

  • DeepSeek-R1$20.53
  • GLM-4.7$10.40
  • Claude Haiku 4.5$20.00
04 — Questions

Which should you choose?

Which is better: DeepSeek-R1, GLM-4.7 or Claude Haiku 4.5?

It is close. Our weighted score puts them within 3 points (Claude Haiku 4.5 60/100, GLM-4.7 57/100, DeepSeek-R1 50/100), so choose by what matters most for your work: GLM-4.7 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, DeepSeek-R1, GLM-4.7 or Claude Haiku 4.5?

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); DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers). 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 $2.05 for DeepSeek-R1 (2.1× 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 DeepSeek-R1 138.6 (#118 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%, DeepSeek-R1 71.7%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — GLM-4.7 83.3%, Claude Haiku 4.5 66.7%, DeepSeek-R1 53.3%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-R1, GLM-4.7 and Claude Haiku 4.5 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 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, GLM-4.7 up to 131,072, Claude Haiku 4.5 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-R1 accepts text; GLM-4.7 accepts text; Claude Haiku 4.5 accepts text, images and PDFs. Claude Haiku 4.5 handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 and GLM-4.7 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; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, GLM-4.7 Apr 2025, Claude Haiku 4.5 Feb 28, 2025.

How do you decide the winner?

This rating uses 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 18, 2026.