ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Grok 4.6 vs Grok 4.20 (Reasoning)

Grok 4.20 (Reasoning) comes out ahead, 68 to 65 on our weighted score, and it is the cheaper option too.

  1. xAI

    Grok 4.6

    Released Aug 12, 2026

    65/100
    • ECI156.6
    • Price$2.00 / $6.00
    • Context500K
    Full specs Remove Grok 4.6
  2. Our pick

    xAI

    Grok 4.20 (Reasoning)

    Released Mar 9, 2026

    68/100
    • ECI152.0
    • Price$1.25 / $2.50
    • Context1M
    Full specs Remove Grok 4.20 (Reasoning)

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Grok 4.20 (Reasoning) is our pick

Grok 4.20 (Reasoning) is the better all-round choice, scoring 68/100 against Grok 4.6 (65). It leads on price, inputs & features and context window. Grok 4.6 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGrok 4.6Capabilities Index (ECI): Grok 4.6 156.6 · Grok 4.20 (Reasoning) 152.0
  • Lowest priceGrok 4.20 (Reasoning)Grok 4.20 (Reasoning) $1.56 · Grok 4.6 $3.00 per 1M tokens (3:1 blend)
  • Longest contextGrok 4.20 (Reasoning)Grok 4.20 (Reasoning) 1,000,000 · Grok 4.6 500,000 tokens
  • Widest inputsGrok 4.20 (Reasoning)Grok 4.6: Text, Images · Grok 4.20 (Reasoning): Text, Images, PDFs
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightGrok 4.6Grok 4.20 (Reasoning)
CapabilityCapabilities Index (ECI)50%8681
Price25%2741
Inputs & features15%7080
Context window10%4860
Overall100%65/10068/100
02 — Side by side

Every spec in one table

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

Grok 4.6 vs Grok 4.20 (Reasoning) specifications side by side
SpecificationGrok 4.6xAIGrok 4.20 (Reasoning)xAI
Capability
Capabilities Index (ECI)156.6 (best)152.0
ECI rank#19 of 148 (best)#41 of 148
GPQA DiamondGraduate-level science questions94.0% (best)89.3%
FrontierMath Tiers 1–3Research-level mathematics66.0% (best)44.9%
OTIS Mock AIME 2024–2025Competition mathematics99.2% (best)92.2%
SimpleQA VerifiedShort factual questions49.3% (best)30.2%
Price per million tokens
Input$2.00$1.25 (best)
Output$6.00$2.50 (best)
Cached input$0.50$0.20 (best)
Blended (3:1)$3.00$1.56 (best)
Long-context rateOver 200K: $4.00 / $12.00Over 200K: $2.50 / $5.00
Price sourceOfficial xAI APIOfficial xAI API
Limits
Context window500,000 tokens1,000,000 tokens (best)
Max output500,000 tokens (best)30,000 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsNoYes
AudioNoNo
VideoNoNo
ReasoningYeslow · medium · high · xhighYes
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDgrok-4.6grok-4.20-0309-reasoning
API providers29 (best)11
ReleasedAug 12, 2026Mar 9, 2026
Knowledge cutoffFeb 1, 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.

  • Grok 4.6$32.00
  • Grok 4.20 (Reasoning)$17.50
04 — Questions

Which should you choose?

Which is better: Grok 4.6 or Grok 4.20 (Reasoning)?

Grok 4.20 (Reasoning) is the better all-round choice, scoring 68/100 against Grok 4.6 (65). It leads on price, inputs & features and context window. Grok 4.6 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Grok 4.6 or Grok 4.20 (Reasoning)?

Grok 4.20 (Reasoning) is cheaper at $1.25 input / $2.50 output per million tokens (official xAI API price). Grok 4.6 costs $2.00 input / $6.00 output per million tokens (official xAI 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 (Reasoning) versus $3.00 for Grok 4.6 (1.9× as much).

Which scores higher on benchmarks?

Grok 4.6 scores higher on the Capabilities Index (ECI): Grok 4.6 156.6 (#19 of 148) and Grok 4.20 (Reasoning) 152.0 (#41 of 148). Their confidence ranges do not overlap (154.7–158.9 vs 149.3–154.4), so the gap is a real one. On individual benchmarks: GPQA Diamond — Grok 4.6 94.0%, Grok 4.20 (Reasoning) 89.3%; FrontierMath Tiers 1–3 — Grok 4.6 66.0%, Grok 4.20 (Reasoning) 44.9%; OTIS Mock AIME 2024–2025 — Grok 4.6 99.2%, Grok 4.20 (Reasoning) 92.2%; SimpleQA Verified — Grok 4.6 49.3%, Grok 4.20 (Reasoning) 30.2%.

Which is better for coding?

There are no published SWE-bench Verified results for Grok 4.6 and Grok 4.20 (Reasoning) yet, so there is no like-for-like coding score. On overall capability, Grok 4.6 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?

Grok 4.20 (Reasoning) has the largest context window at 1,000,000 tokens, against 500,000 for Grok 4.6. Maximum output per response: Grok 4.6 up to 500,000, Grok 4.20 (Reasoning) up to 30,000 tokens.

Which can read images, PDFs, audio or video?

Grok 4.6 accepts text and images; Grok 4.20 (Reasoning) accepts text, images and PDFs. Grok 4.20 (Reasoning) handles the widest range of inputs.

Are any of these open source?

No. Grok 4.6 and Grok 4.20 (Reasoning) are proprietary and only available through APIs and apps.

Which is newer?

Grok 4.6 is the newest, released Aug 12, 2026. Grok 4.20 (Reasoning) came out Mar 9, 2026. Knowledge cutoff: Grok 4.6 Feb 1, 2026.

How do you decide the winner?

Each model gets a 0–100 score on 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons