How does GPT-5.2 rank among AI models?
GPT-5.2 is a superseded version and is not on the current board as of 22 September 2026.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.
OpenAI·openai/gpt-5.2
GPT-5.2 is ModelCap archive rank #78 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.
GPT-5.2 listed OpenRouter input price is $1.75 per 1M tokens and listed output price is $14.00 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.
GPT-5.2 has a published context limit of 400K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.
GPT-5.2 has 4 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.
GPT-5.2 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
67.5#78
Measured · 66% support · score interval 62.7–72.3
Evidence as of 21 Sept 2026, 17:21 UTC
Superseded by GPT-5.5. It no longer holds a current-board position; its all-versions archive rank is #78.
Input
$1.75
per 1M tokens
Output
$14.00
per 1M tokens
Context
400K
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 (6)
ModelCap Index · All-versions archive
Methodology67.5
Measured · 3 public benchmark observations across 3 boards
All-versions archive
#78
- Public rank basis
- Measured (measured)
- Index support
- 65.6% · strong
- Index interval
- 62.7–72.3
- 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 · openai/openai/gpt-5.2 · aggregates disclosed benchmark configurations · endpoint configuration not claimed
- Index observations used
- 3
- Qualified Index evidence point
- 67.5
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
- 67.5
- Evidence status
- confirmed · 87% mass
- General preference
- 68.0
- Coding
- 67.8
- Agents & tools
- —
- Reasoning
- 51.9
- Evidence breadth
- 95%
- Evidence coverage
- 66%
Market and catalogue signals · secondary, never the language Index rank
- Usage (OpenRouter popularity)
- 19.1
- Liquidity (providers × uptime)
- 98.9
- Open reach (HF downloads)
- —
- Surface (context / tools / modalities)
- 93.3
- Freshness
- 33.7
- · OpenRouter popularity #107
- · 2 live providers
- · Catalogue: context 400000, reasoning, tools, modalities File/Image/Text
- · First seen 2025-12-10
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 · High68.0
- Arena Coding · High67.8
- ARC-AGI-2 Verified · X-High51.9
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 index48.5
partial · 56% metadata coverage
- Artifact reproducibility
- 0.0
- Access & legal clarity
- 30.3
- Deployability
- 90.0
- Evaluation provenance
- 77.0
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
- 44.4
- OpenRouter weekly popularity
- #107 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
- Status
- Ranked
- Source
- LMArena
- Official rank
- #91 of 402
- Rating
- 1435.8
- 95% confidence interval
- 1433–1439
- Votes
- 79K
- Source published at
- 13 Sept 2026, 00:00 UTC
- Category
- overall
- Identity match confidence
- 100%
Market Gravity breakdown
- Usage55%
- 19.1
- Liquidity25%
- 98.9
- Open reach15%
- 50.0
- Freshness5%
- 33.7
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
- 400K tokens
- Max output
- 128K tokens
- Inputs
- File, Image, Text
- Outputs
- Text
- Tokenizer
- GPT
- Cached input tokens
- $0.175 / 1M
- First seen on OpenRouter
- 10 Dec 2025
Capabilities
- Supported: Reasoning
- Supported: Tool use
- Supported: Structured output
- Supported: Response format
- Supported: Moderated
Benchmark leaderboards featuring GPT-5.2
All leaderboardsGPT-5.2: common questions
How much does GPT-5.2 cost per 1M tokens?
GPT-5.2 is listed at $1.75 per 1M input tokens and $14.00 per 1M output tokens as of 22 September 2026; the lowest output price among 2 providers is $7.00 on OpenAI. 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 $10.50 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 GPT-5.2?
GPT-5.2 has a published context window of 400K tokens (400,000) and a maximum output of 128K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.
Is GPT-5.2 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 GPT-5.2?
2 providers serve GPT-5.2 through OpenRouter as of 22 September 2026: OpenAI and Azure. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Which benchmarks has GPT-5.2 been evaluated on?
GPT-5.2 has published results on 5 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1489 (#83 of 397), ARC-AGI-2 52.9% (#70 of 214), SWE-bench 72.8% (#7 of 47), AA τ²-Bench Telecom 84.8% (#102 of 436) and AA Humanity's Last Exam 37.7% (#74 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.
When was GPT-5.2 released?
GPT-5.2 first appeared in the catalogue on 10 Dec 2025. It has since been superseded by GPT-5.5. Rank and price movements since then are recorded on the site's changes feed.