How does Grok 4.20 rank among AI models?
Grok 4.20 is a superseded version and is not on the current board as of 22 September 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.
xAI·x-ai/grok-4.20
Grok 4.20 is ModelCap archive rank #26 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.
Grok 4.20 listed OpenRouter input price is $1.25 per 1M tokens and listed output price is $2.50 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.
Grok 4.20 has a published context limit of 2M tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.
Grok 4.20 has 4 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.
Grok 4.20 weight access is api only, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.
Snapshot facts · download the public dataset · methodology
ModelCap Index · All-versions archive
79.5#26
Measured · 65% support · score interval 74.7–84.3
Evidence as of 21 Sept 2026, 17:21 UTC
Superseded by Grok 4.7. It no longer holds a current-board position; its all-versions archive rank is #26.
Input
$1.25
per 1M tokens
Output
$2.50
per 1M tokens
Context
2M
tokens
Providers
4
endpoints
Gateway spend
—
latest · Vercel share
Providers
Uptime measured over the last 30 minutesReasoning efforts
Best supported result can inform ModelCapPublished Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.
Related community configurations
Human preference ratingOther versions (4)
ModelCap Index · All-versions archive
Methodology79.5
Measured · 4 public benchmark observations across 4 boards
All-versions archive
#26
- Public rank basis
- Measured (measured)
- Index support
- 65.3% · strong
- Index interval
- 74.7–84.3
- Rank posterior
- Not available
- Top 5 / Top 10 probability
- Not available / Not available
- Posterior as of
- Snapshot timestamp unavailable
- Evidence as of
- 21 Sept 2026, 17:21 UTC
- Identity binding
- Exact catalogue product · x-ai/x-ai/grok-4.20 · aggregates disclosed benchmark configurations · endpoint configuration not claimed
- Index observations used
- 4
- Qualified Index evidence point
- 79.5
Bayesian Evidence Score · measured evidence input only
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
- Observed capability
- 79.5
- Evidence status
- confirmed · 87% mass
- General preference
- 80.7
- Coding
- 76.2
- Agents & tools
- —
- Reasoning
- 51.1
- Evidence breadth
- 95%
- Evidence coverage
- 65%
Market and catalogue signals · secondary, never the language Index rank
- Usage (OpenRouter popularity)
- 18.6
- Liquidity (providers × uptime)
- 97.3
- Open reach (HF downloads)
- —
- Surface (context / tools / modalities)
- 100.0
- Freshness
- 51.5
- · OpenRouter popularity #110
- · 1 live provider
- · Catalogue: context 2000000, reasoning, tools, modalities Text/Image/File
- · First seen 2026-03-31
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
BES evidence selected · measured input only
- Arena Overall · Beta180.7
- Arena Coding · Beta · 0309 · Reasoning76.2
- ARC-AGI-2 Verified · Reasoning62.1
- ARC-AGI-3 Verified · Reasoning25.7
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Deployment readiness
Metadata index45.4
partial · 56% metadata coverage
- Artifact reproducibility
- 0.0
- Access & legal clarity
- 30.3
- Deployability
- 79.9
- Evaluation provenance
- 76.9
Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market activity
Venue coverage- Market Gravity
- 44.6
- OpenRouter weekly popularity
- #110 of 322
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
Arena preference
Configuration results available
Arena has published current community results for Beta · 0309 · Reasoning and Beta1. No default-configuration result is published, so the raw Arena field stays configuration-specific. The strongest supported result can still inform ModelCap Score with reduced confidence.
Current board through 13 Sept 2026, 00:00 UTC
Market Gravity breakdown
- Usage55%
- 18.6
- Liquidity25%
- 97.3
- Open reach15%
- 50.0
- Freshness5%
- 51.5
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
Specification
- Context window
- 2M tokens
- Max output
- 1.8M tokens
- Inputs
- Text, Image, File
- Outputs
- Text
- Tokenizer
- Grok
- Cached input tokens
- $0.20 / 1M
- First seen on OpenRouter
- 31 Mar 2026
- Knowledge cutoff
- 2025-09-01
Capabilities
- Supported: Reasoning
- Supported: Tool use
- Supported: Structured output
- Supported: Response format
- Not supported: Moderated
Benchmark leaderboards featuring Grok 4.20
All leaderboardsGrok 4.20: common questions
How much does Grok 4.20 cost per 1M tokens?
Grok 4.20 is listed at $1.25 per 1M input tokens and $2.50 per 1M output tokens as of 22 September 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $3.75 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.
What is the context window of Grok 4.20?
Grok 4.20 has a published context window of 2M tokens (2,000,000) and a maximum output of 1.8M tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.
Is Grok 4.20 open-weight?
API only. No downloadable model weights are linked in the current source data; access is through a hosted API or product.
Which API providers serve Grok 4.20?
One provider serves Grok 4.20 through OpenRouter as of 22 September 2026: xAI. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Which benchmarks has Grok 4.20 been evaluated on?
Grok 4.20 has published results on 5 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1510 (#47 of 397), ARC-AGI-2 65.1% (#47 of 214), ARC-AGI-3 0.1% (#36 of 39), AA τ²-Bench Telecom 93.0% (#47 of 436) and AA Humanity's Last Exam 34.5% (#91 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.
When was Grok 4.20 released?
Grok 4.20 first appeared in the catalogue on 31 Mar 2026, with a published knowledge cutoff of 2025-09-01. It has since been superseded by Grok 4.7. Rank and price movements since then are recorded on the site's changes feed.