ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek V4 Pro 0813 vs GLM-5.3-Flash vs Mistral Large 4

GLM-5.3-Flash comes out ahead, 80 to 77 and 73 on our weighted score, and it is the cheaper option too.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    73/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
  2. Our pick

    Z.ai (Zhipu)

    GLM-5.3-Flash

    Released Aug 26, 2026

    80/100
    • ECI153.8
    • Price$0.15 / $0.50
    • Context1M
  3. Mistral AI

    Mistral Large 4

    Released Oct 6, 2026NewBeta

    77/100
    • ECI154.6
    • Price$0.70 / $2.10
    • Context1.05M
01 — Verdict

GLM-5.3-Flash is our pick

GLM-5.3-Flash is the better all-round choice, scoring 80/100 against Mistral Large 4 (77) and DeepSeek V4 Pro 0813 (73). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityDeepSeek V4 Pro 0813Capabilities Index (ECI): DeepSeek V4 Pro 0813 156.0 · Mistral Large 4 154.6 · GLM-5.3-Flash 153.8
  • Lowest priceGLM-5.3-FlashGLM-5.3-Flash $0.237 · DeepSeek V4 Pro 0813 $0.99 · Mistral Large 4 $1.05 per 1M tokens (3:1 blend)
  • Longest contextMistral Large 4Mistral Large 4 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 · GLM-5.3-Flash 1,000,000 tokens
  • Widest inputsGLM-5.3-FlashDeepSeek V4 Pro 0813: Text · GLM-5.3-Flash: Text, Images, PDFs, Video · Mistral Large 4: Text, Images
  • Self-hostingDeepSeek V4 Pro 0813 and GLM-5.3-FlashPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek V4 Pro 0813GLM-5.3-FlashMistral Large 4
CapabilityCapabilities Index (ECI)67%838182
Inputs & features20%459070
Context window13%646465
Overall100%73/10080/10077/100
02 — Side by side

Every spec in one table

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

DeepSeek V4 Pro 0813 vs GLM-5.3-Flash vs Mistral Large 4 specifications side by side
SpecificationDeepSeek V4 Pro 0813DeepSeekGLM-5.3-FlashZ.ai (Zhipu)Mistral Large 4Mistral AI
Capability
Capabilities Index (ECI)156.0 (best)153.8154.6
ECI rank#42 of 158 (best)#53 of 158#50 of 158
GPQA DiamondGraduate-level science questions91.7% (best)90.2%90.2%
FrontierMath Tiers 1–3Research-level mathematics64.6% (best)55.8%—
OTIS Mock AIME 2024–2025Competition mathematics98.6%93.9%99.4% (best)
SimpleQA VerifiedShort factual questions52.9% (best)—22.4%
Price per million tokens
Input$0.66$0.15 (best)$0.70
Output$1.98$0.50 (best)$2.10
Cached input$0.022 (best)$0.03$0.07
Blended (3:1)$0.99$0.237 (best)$1.05
Long-context rateSame rateSame rateSame rate
Price sourceOfficial DeepSeek APIOfficial Z.AI APIOfficial Mistral API
Limits
Context window1,000,000 tokens1,000,000 tokens1,048,576 tokens (best)
Max output384,000 tokens (best)131,072 tokens262,144 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoYesNo
ReasoningYeslow · high · maxYeslow · high · maxYeslow · medium · high
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsOpenMITOpenProprietary
API model IDdeepseek-v4-proglm-5.3-flashmistral-large-4
API providers54124 (best)16
ReleasedAug 13, 2026Aug 26, 2026Oct 6, 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 V4 Pro 0813$10.56
  • GLM-5.3-Flash$2.50
  • Mistral Large 4$11.20
04 — Questions

Which should you choose?

Which is better: DeepSeek V4 Pro 0813, GLM-5.3-Flash or Mistral Large 4?

GLM-5.3-Flash is the better all-round choice, scoring 80/100 against Mistral Large 4 (77) and DeepSeek V4 Pro 0813 (73). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek V4 Pro 0813, GLM-5.3-Flash or Mistral Large 4?

GLM-5.3-Flash is cheaper at $0.15 input / $0.50 output per million tokens (official Z.AI API price). DeepSeek V4 Pro 0813 costs $0.66 input / $1.98 output per million tokens (official DeepSeek API price); Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.237 per million tokens for GLM-5.3-Flash versus $0.99 for DeepSeek V4 Pro 0813 (4.2× as much) and $1.05 for Mistral Large 4 (4.4× as much).

Which scores higher on benchmarks?

DeepSeek V4 Pro 0813 scores higher on the Capabilities Index (ECI): DeepSeek V4 Pro 0813 156.0 (#42 of 158), Mistral Large 4 154.6 (#50 of 158) and GLM-5.3-Flash 153.8 (#53 of 158). The confidence ranges of the top two overlap (154.1–158.0 vs 151.8–157.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek V4 Pro 0813 91.7%, GLM-5.3-Flash 90.2%, Mistral Large 4 90.2%; OTIS Mock AIME 2024–2025 — Mistral Large 4 99.4%, DeepSeek V4 Pro 0813 98.6%, GLM-5.3-Flash 93.9%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V4 Pro 0813, GLM-5.3-Flash and Mistral Large 4 yet, so there is no like-for-like coding score. On overall capability, DeepSeek V4 Pro 0813 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?

Mistral Large 4 has the largest context window at 1,048,576 tokens, against 1,000,000 for DeepSeek V4 Pro 0813 and 1,000,000 for GLM-5.3-Flash. Maximum output per response: DeepSeek V4 Pro 0813 up to 384,000, GLM-5.3-Flash up to 131,072, Mistral Large 4 up to 262,144 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V4 Pro 0813 accepts text; GLM-5.3-Flash accepts text, images, PDFs and video; Mistral Large 4 accepts text and images. GLM-5.3-Flash handles the widest range of inputs.

Are any of these open source?

DeepSeek V4 Pro 0813 and GLM-5.3-Flash publishes its weights (MIT) and can be self-hosted; Mistral Large 4 is proprietary.

Which is newer?

Mistral Large 4 is the newest, released Oct 6, 2026. GLM-5.3-Flash came out Aug 26, 2026; DeepSeek V4 Pro 0813 came out Aug 13, 2026.

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.