Skip to content

OpenAI · Chat

GPT-5.2 Pro

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.

Newer version: GPT-5.5 Pro. Our catalogue has no release date for GPT-5.2 Pro. We compared the version names in our catalogue.

From Aiml API's listing:
GPT-5.2 Pro is the flagship GPT-5.2 variant offering maximum output size and reasoning depth.
llminfo IQ
134.7
Max context
400K
Listings
31

Evidence and sources

llminfo IQ 134.7, ranked among chat models. From 42 benchmarks. Plenty of data behind it.How llminfo IQ is computedFair value (49.6). Costs per task about what its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksMaker HQ: US (according to OpenAI's own website)
All rankings: #559 on OpenRouter today #562 on OpenRouter this week #604 on OpenRouter this monthSources: OpenAI API data, Models.dev data, GenAI Prices data, AI/ML API dataPrimary data from OpenAI API from Models.dev: name, weights availability from GenAI Prices: variant from AI/ML API: primary mode, description

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchBatch API

Listings

 OpenAIgpt-5.2-proSources: GenAI Prices data, LiteLLM data, Models.dev data, OpenAI API data272K$21.00batch $10.50$168.00batch $84.00
 Flowdotgpt-5.2-pro-2025-12-11 · 2025-12-11Source: FlowDot data200K$5.00$15.00
 Microsoft Azuregpt-5.2-pro-batch · batchSource: Helicone Costs dataNot published by the provider$10.50$84.00
 OpenRouteropenai/gpt-5.2-pro:batch · batchSource: OpenRouter data docs400K$10.50$84.00
 Poeopenai/gpt-5.2-proSource: Models.dev data400K$19.091$152.73
 Jiekougpt-5.2-proSource: Models.dev data400K$19.95$159.60
 Aihubmixgpt-5.2-proSource: AIHubMix data docs400K$21.00cache read $2.10$168.00
 Cometapigpt-5.2-proSources: CometAPI data, CometAPI Pricing dataNot published by the provider$21.00$168.00
 Eden AIInference by OpenAIopenai/gpt-5.2-proSource: Models.dev data400K$21.00$168.00
 Fastrouteropenai/gpt-5.2-proSource: FastRouter data400K$21.00batch $10.50$168.00batch $84.00
Show all 28 listings

Showing 10 of 28: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Digitalocean, Kilo, Llmgateway, Llmgateway Providers, Nous Portal, Orcarouter, Vercel, Zenmux.

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Reasoning

ARC-AGI4 related benchmarks · 10 results
ARC-AGI
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Verified · high effort
ARC-AGI-1
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · Verified
Effort not reported
v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reasoning effort · no tools
Effort not reported
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Agentic

BrowseComp3 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table
standard tool-use setup · xhigh
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GDPval4 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ties allowed · ChatGPT heavy
wins · no ties · ChatGPT heavy

Math

AIME 20252 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
HMMT Feb 25Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.4 launch table

Knowledge

Multilingual

General

Human preference

Other

ArmBench-LLM Armenian22 related benchmarks · 44 results
arak (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
conversation (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
dream (exact_match_mcqa, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
email (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
exam_history (armenian_exam_score, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
exam_literature (armenian_exam_score, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
Show 32 more resultsHide 32 results
exam_math (armenian_exam_score, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
finer (ner_accuracy, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
hartak (exact_match_mcqa, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
mmlu_pro (armenian_mmlu_pro_score, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
ms_marco (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
paraphrase (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
pioner (ner_accuracy, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
pos (ud_pos_regex_acc, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
punctuation (punctuation_accuracy, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
scientific (exact_match_mcqa, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
sentiment (exact_match_mcqa, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
short_sentences_translation (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
space_fix (space_accuracy, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
squad (bleu, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
syndarin (exact_match_mcqa, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
topic-14class (exact_match_mcqa, 0-shot)
Source: ArmBench-LLM Armenian data docs
Setting not stated
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
internal spreadsheet tasks · ChatGPT heavy
OpenAI internal benchmark

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · ArmBench-LLM by Metric-AI. Public numeric primary task results; no separate results licence asserted. · MineBench, MIT (licence)

Around the web

Also known as: azure/eu/gpt-5.2-pro, azure/gpt-5.2-pro, azure/gpt-5.2-pro-2025-12-11, azure/us/gpt-5.2-pro, gpt-5.2-pro-2025-12-11, openai-gpt-5.2-pro, openai/gpt-5-2-pro, openai/gpt-5.2-pro, openai/gpt-5.2-pro-2025-12-11, openai/gpt-5.2-pro:batch

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works