ZMIME
Comparison · 2 models · Updated Nov 18, 2026

DeepSeek R1 0528 vs GLM-5

GLM-5 comes out ahead, 62 to 57 on our weighted score, though DeepSeek R1 0528 is 40% cheaper per token.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    57/100
    • ECI140.8
    • Price$0.512 / $2.19
    • Context164K
  2. Our pick

    Z.ai (Zhipu)

    GLM-5

    Released Feb 12, 2026

    62/100
    • ECI146.5
    • Price$1.00 / $3.20
    • Context205K
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

GLM-5 is our pick

GLM-5 is the better all-round choice, scoring 62/100 against DeepSeek R1 0528 (57). It leads on capability and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGLM-5Capabilities Index (ECI): GLM-5 146.5 · DeepSeek R1 0528 140.8
  • Lowest priceDeepSeek R1 0528DeepSeek R1 0528 $0.932 · GLM-5 $1.55 per 1M tokens (3:1 blend)
  • Longest contextGLM-5GLM-5 204,800 · DeepSeek R1 0528 163,840 tokens
  • Widest inputsSame inputsDeepSeek R1 0528: Text · GLM-5: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek R1 0528GLM-5
CapabilityCapabilities Index (ECI)67%6974
Inputs & features20%3535
Context window13%3639
Overall100%57/10062/100
02 — Side by side

Every spec in one table

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

DeepSeek R1 0528 vs GLM-5 specifications side by side
SpecificationDeepSeek R1 0528DeepSeekGLM-5Z.ai (Zhipu)
Capability
Capabilities Index (ECI)140.8146.5 (best)
ECI rank#113 of 158#85 of 158 (best)
GPQA DiamondGraduate-level science questions76.3%87.8% (best)
OTIS Mock AIME 2024–2025Competition mathematics66.4%80.0% (best)
SWE-bench VerifiedFixing real GitHub issues—72.1%
Price per million tokens
Input$0.512 (best)$1.00
Output$2.19 (best)$3.20
Cached input—$0.20
Blended (3:1)$0.932 (best)$1.55
Long-context rateSame rateSame rate
Price sourceMedian of 16 providersOfficial Z.AI API
Limits
Context window163,840 tokens204,800 tokens (best)
Max output32,768 tokens131,072 tokens (best)
Inputs and features
TextYesYes
ImagesNoNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningYesYes
Tool callingYesYes
Structured outputNoNo
Availability
WeightsOpenMITOpen
API model ID—glm-5
API providers1637 (best)
ReleasedMay 28, 2025Feb 12, 2026
Knowledge cutoff——
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 0528$9.50
  • GLM-5$16.40
04 — Questions

Which should you choose?

Which is better: DeepSeek R1 0528 or GLM-5?

GLM-5 is the better all-round choice, scoring 62/100 against DeepSeek R1 0528 (57). It leads on capability and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek R1 0528 or GLM-5?

DeepSeek R1 0528 is cheaper at $0.512 input / $2.19 output per million tokens (median across 16 API providers). GLM-5 costs $1.00 input / $3.20 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.932 per million tokens for DeepSeek R1 0528 versus $1.55 for GLM-5 (1.7× as much).

Which scores higher on benchmarks?

GLM-5 scores higher on the Capabilities Index (ECI): GLM-5 146.5 (#85 of 158) and DeepSeek R1 0528 140.8 (#113 of 158). Their confidence ranges do not overlap (145.0–148.1 vs 138.9–142.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — GLM-5 87.8%, DeepSeek R1 0528 76.3%; OTIS Mock AIME 2024–2025 — GLM-5 80.0%, DeepSeek R1 0528 66.4%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek R1 0528 yet, so there is no like-for-like coding score. On overall capability, GLM-5 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

GLM-5 has the largest context window at 204,800 tokens, against 163,840 for DeepSeek R1 0528. Maximum output per response: DeepSeek R1 0528 up to 32,768, GLM-5 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

DeepSeek R1 0528 accepts text; GLM-5 accepts text. They handle the same number of input types.

Are any of these open source?

Yes, both publish their weights (MIT), so you can self-host them.

Which is newer?

GLM-5 is the newest, released Feb 12, 2026. DeepSeek R1 0528 came out May 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.