ZMIME
Comparison · 3 models · Updated Nov 22, 2026

GLM-5.1 vs Grok 4.20 (Non-Reasoning) vs DeepSeek V4 Pro

No independent capability benchmark covers every model here yet. The score uses price and context window.No independent capability benchmark covers every model here yet. The score uses context window.

  1. Z.ai (Zhipu)

    GLM-5.1

    Released Apr 7, 2026

    34/100
    • ECI150.7
    • Price$1.40 / $4.40
    • Context200K
  2. xAI

    Grok 4.20 (Non-Reasoning)

    Released Mar 9, 2026

    46/100
    • ECI—
    • Price$1.25 / $2.50
    • Context1M
  3. DeepSeek

    DeepSeek V4 Pro

    Released Apr 24, 2026

    42/100
    • ECI150.2
    • Price$1.60 / $3.33
    • Context1M
  4. Z.ai (Zhipu)

    GLM-5.1

    Released Apr 7, 2026

    39/100
    • ECI150.7
    • Price$1.40 / $4.40
    • Context200K
  5. xAI

    Grok 4.20 (Non-Reasoning)

    Released Mar 9, 2026

    64/100
    • ECI—
    • Price$1.25 / $2.50
    • Context1M
  6. DeepSeek

    DeepSeek V4 Pro

    Released Apr 24, 2026

    64/100
    • ECI150.2
    • Price$1.60 / $3.33
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Non-Reasoning) 46/100, DeepSeek V4 Pro 42/100, GLM-5.1 34/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Non-Reasoning) 64/100, DeepSeek V4 Pro 64/100, GLM-5.1 39/100) compare the available specifications only. The score weighs context window 100%. 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 priceGrok 4.20 (Non-Reasoning)Grok 4.20 (Non-Reasoning) $1.56 · DeepSeek V4 Pro $2.03 · GLM-5.1 $2.15 per 1M tokens (3:1 blend)
  • Longest contextGrok 4.20 (Non-Reasoning) and DeepSeek V4 ProGrok 4.20 (Non-Reasoning) 1,000,000 · DeepSeek V4 Pro 1,000,000 · GLM-5.1 200,000 tokens
  • Widest inputsGrok 4.20 (Non-Reasoning)GLM-5.1: Text · Grok 4.20 (Non-Reasoning): Text, Images, PDFs · DeepSeek V4 Pro: Text
  • Self-hostingGLM-5.1 and DeepSeek V4 ProPublishes downloadable weights
How the score is built
MeasureWeightGLM-5.1Grok 4.20 (Non-Reasoning)DeepSeek V4 Pro
Price71%333934
Context window29%396464
Specs & price only100%34/10046/10042/100

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

How the score is built
MeasureWeightGLM-5.1Grok 4.20 (Non-Reasoning)DeepSeek V4 Pro
Context window100%396464
Specs only100%39/10064/10064/100

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

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

GLM-5.1 vs Grok 4.20 (Non-Reasoning) vs DeepSeek V4 Pro specifications side by side
SpecificationGLM-5.1Z.ai (Zhipu)Grok 4.20 (Non-Reasoning)xAIDeepSeek V4 ProDeepSeek
Capability
Capabilities Index (ECI)150.7 (best)Not published150.2
ECI rank#67 of 159 (best)Not published#68 of 159
ECI confidence interval148.7–152.8Not published148.4–152.0
ECI evaluation dateApr 7, 2026Not publishedApr 24, 2026
Documented capabilitiesStrong GLM coding model for agentic engineering, terminals, and repository generationGrok model for agentic tool use, reasoning, coding, and live assistanceOpen MoE flagship with million-token context for coding and long agent runs
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questions89.9%Not published90.9%high (best)
FrontierMath Tiers 1–3Research-level mathematics36.8%Not published45.3%max (best)
OTIS Mock AIME 2024–2025Competition mathematics93.3%Not published96.7%max (best)
SWE-bench VerifiedFixing real GitHub issues74.2%Not published77.6%max (best)
SimpleQA VerifiedShort factual questions34.0%Not published47.0%max (best)
Publisher-reported benchmarks
Artificial Analysis Coding Agent IndexPublisher-reported result52.7average pass@1Reported resultNot publishedNot published
SWE-Atlas Codebase QnAPublisher-reported result73.2pass@1Reported resultNot publishedNot published
SWE-Bench Pro · hard-aaPublisher-reported result19.8pass@1Reported resultNot publishedNot published
Terminal-Bench 2.1Publisher-reported result65.1pass@1Reported resultNot publishedNot published
SWE-Bench VerifiedPublisher-reported resultNot publishedNot published80.6resolvedReported result
Artificial Analysis Coding Agent IndexhighNot publishedNot published50.1average pass@1Reported result
SWE-Atlas Codebase QnAhighNot publishedNot published67.8pass@1Reported result
SWE-Bench Pro · hard-aahighNot publishedNot published18pass@1Reported result
Terminal-Bench 2.1highNot publishedNot published64.7pass@1Reported result
MMLU-Propreview checkpoint; max effortNot publishedNot published87.5EMReported result
SimpleQA-Verifiedpreview checkpoint; max effortNot publishedNot published57.9pass@1Reported result
Chinese SimpleQApreview checkpoint; max effortNot publishedNot published84.4pass@1Reported result
GPQA Diamondpreview checkpoint; max effortNot publishedNot published90.1pass@1Reported result
Humanity's Last Exampreview checkpoint; max effort; without toolsNot publishedNot published37.7pass@1Reported result
LiveCodeBenchpreview checkpoint; max effortNot publishedNot published93.5pass@1Reported result
Codeforcespreview checkpoint; max effortNot publishedNot published3206ratingReported result
HMMT · February 2026preview checkpoint; max effortNot publishedNot published95.2pass@1Reported result
IMOAnswerBenchpreview checkpoint; max effortNot publishedNot published89.8pass@1Reported result
MathArena Apexpreview checkpoint; max effortNot publishedNot published38.3pass@1Reported result
MathArena Apex Shortlistpreview checkpoint; max effortNot publishedNot published90.2pass@1Reported result
MRCR · 1M contextpreview checkpoint; max effortNot publishedNot published83.5MMRReported result
CorpusQA · 1M contextpreview checkpoint; max effortNot publishedNot published62accuracyReported result
Terminal-Bench 2.0preview checkpoint; max effortNot publishedNot published67.9accuracyReported result
SWE-Bench Propreview checkpoint; max effortNot publishedNot published55.4resolvedReported result
SWE-Bench Multilingualpreview checkpoint; max effortNot publishedNot published76.2resolvedReported result
BrowseComppreview checkpoint; max effortNot publishedNot published83.4pass@1Reported result
Humanity's Last Exampreview checkpoint; max effort; with toolsNot publishedNot published48.2pass@1Reported result
MCP Atlas · publicpreview checkpoint; max effortNot publishedNot published73.6pass@1Reported result
GDPval-AApreview checkpoint; max effortNot publishedNot published1554EloReported result
Toolathlonpreview checkpoint; max effortNot publishedNot published51.8pass@1Reported result
Price per million tokens
Input$1.40$1.25 (best)$1.60
Output$4.40$2.50 (best)$3.33
Cached input$0.26$0.20 (best)Not published
Blended (3:1)$2.15$1.56 (best)$2.03
Long-context rateSame rateOver 200K: $2.50 / $5.00Same rate
Price sourceOfficial Z.AI APIOfficial xAI APIMedian of 65 providers
Limits
Context window200,000 tokens1,000,000 tokens (best)1,000,000 tokens (best)
Max inputNot publishedNot publishedNot published
Max output131,072 tokens30,000 tokens384,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputYesYesNot published
File attachmentsNoYesNo
Temperature controlYesYesYes
Reasoning controltoggleNot publishedalways
Availability
WeightsOpenProprietaryOpen
API model IDglm-5.1grok-4.20-0309-non-reasoningNot published
API providers451367 (best)
ReleasedApr 7, 2026Mar 9, 2026Apr 24, 2026
Knowledge cutoffNot publishedNot publishedMay 2025
Publisher documentationPublisher documentation · Model weightsPublisher documentationModel weights
Source metadata updatedApr 7, 2026Mar 9, 2026Apr 24, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
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-5.1$22.80
  • Grok 4.20 (Non-Reasoning)$17.50
  • DeepSeek V4 Pro$22.66
04 — Questions

Which should you choose?

Which is better: GLM-5.1, Grok 4.20 (Non-Reasoning) or DeepSeek V4 Pro?

There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Non-Reasoning) 46/100, DeepSeek V4 Pro 42/100, GLM-5.1 34/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Grok 4.20 (Non-Reasoning) 64/100, DeepSeek V4 Pro 64/100, GLM-5.1 39/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, GLM-5.1, Grok 4.20 (Non-Reasoning) or DeepSeek V4 Pro?

Grok 4.20 (Non-Reasoning) is cheaper at $1.25 input / $2.50 output per million tokens (official xAI API price). DeepSeek V4 Pro costs $1.60 input / $3.33 output per million tokens (median across 65 API providers); GLM-5.1 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $1.56 per million tokens for Grok 4.20 (Non-Reasoning) versus $2.03 for DeepSeek V4 Pro (1.3× as much) and $2.15 for GLM-5.1 (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GLM-5.1 has an ECI of 150.7, Grok 4.20 (Non-Reasoning) has not been scored yet and DeepSeek V4 Pro has an ECI of 150.2.

Which is better for coding?

There are no published SWE-bench Verified results for Grok 4.20 (Non-Reasoning) 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?

Grok 4.20 (Non-Reasoning) and DeepSeek V4 Pro have the largest context windows (1,000,000 and 1,000,000 tokens), against 200,000 for GLM-5.1. Maximum output per response: GLM-5.1 up to 131,072, Grok 4.20 (Non-Reasoning) up to 30,000, DeepSeek V4 Pro up to 384,000 tokens.

Which can read images, PDFs, audio or video?

GLM-5.1 accepts text; Grok 4.20 (Non-Reasoning) accepts text, images and PDFs; DeepSeek V4 Pro accepts text. Grok 4.20 (Non-Reasoning) handles the widest range of inputs.

Are any of these open source?

GLM-5.1 and DeepSeek V4 Pro publishes its weights and can be self-hosted; Grok 4.20 (Non-Reasoning) is proprietary.

Which is newer?

DeepSeek V4 Pro is the newest, released Apr 24, 2026. GLM-5.1 came out Apr 7, 2026; Grok 4.20 (Non-Reasoning) came out Mar 9, 2026. Knowledge cutoff: DeepSeek V4 Pro May 2025.

How do you decide the winner?

This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.