llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGPT-5.2

OpenAI model product

GPT-5.2

GPT‑5.2 introduces substantial gains in professional knowledge work, outperforming experts on GDPval with 70.9% wins or ties, and setting new highs in coding (SWE‑Bench Pro 55.6%), science (GPQA Diamond ~92–93%), math (AIME 2025: 100%), long‑context accuracy up to 256k tokens, and reliable tool‑calling (Tau2 Telecom 98.7%). It rolls out as Instant, Thinking, and Pro—faster, more structured, and less error‑prone—priced at $1.75/1M input and $14/1M output tokens, with Pro variants supporting xhigh reasoning for top‑quality, end‑to‑end execution.

Updated Aug 10, 2026. Default version: GPT-5.2

Compare
LLMBoard score69.1GPT-5.2
Coverage100%10 benchmark families
Context window400KTokens
Official input price$1.75OpenAI API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
GPT-5.2
Released
Dec 11, 2025
Knowledge cutoff
Aug 25, 2025
Parameters
N/A
Context window
400K
Max output
128K
Inputs
image, text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

GPT-5.2 category scores

Benchmark results

Published benchmark records for the scored version GPT-5.2.

24 rows
Columns

Show columns

BrowseComp Long Context 128k0.915100.0%CAug 7, 2026
BrowseComp Long Context 256k0.912100.0%CAug 7, 2026
Graphwalks BFS <128k0.9122100.0%CAug 7, 2026
AIME 20251.0211499.1%CAug 7, 2026
HMMT 20251.023396.9%CAug 7, 2026
ScreenSpot Pro0.922495.7%CAug 7, 2026
Graphwalks parents <128k0.931888.2%CAug 7, 2026
SWE-Lancer (IC-Diamond subset)0.73660.0%CAug 7, 2026
Tau2 Telecom1.043591.2%CAug 7, 2026
VideoMMMU0.942688.0%CAug 7, 2026
ARC-AGI0.95733.3%CAug 7, 2026
FrontierMath0.451775.0%CAug 7, 2026
Tau2 Retail0.862680.0%CAug 7, 2026
ARC-AGI v20.581653.3%CAug 7, 2026
MMMLU0.994983.3%CAug 7, 2026
GPQA0.91323394.8%CAug 7, 2026
CharXiv-R0.8144771.7%CAug 7, 2026
SWE-Bench Verified0.81410487.4%CAug 7, 2026
MMMU-Pro0.8156578.1%CAug 7, 2026
LiveBench0.7163859.5%BAug 7, 2026
Toolathlon0.5203136.7%CAug 7, 2026
MCP Atlas0.6263013.8%CAug 7, 2026
BrowseComp0.7315847.4%CAug 7, 2026
Humanity's Last Exam0.3419256.0%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$1.75 input, $14 output per 1M
Official provider
OpenAI
Lowest third-party
N/A
Tracked offerings
1
1 rows
Columns

Show columns

OpenAIgpt-5.2global$1.75$14400KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GPT-5.2 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

GPT-5.2Dec 11, 202569.1N/A400K128KNoProprietary

What is GPT-5.2?

A concise description based on the published model registry.

GPT‑5.2 introduces substantial gains in professional knowledge work, outperforming experts on GDPval with 70.9% wins or ties, and setting new highs in coding (SWE‑Bench Pro 55.6%), science (GPQA Diamond ~92–93%), math (AIME 2025: 100%), long‑context accuracy up to 256k tokens, and reliable tool‑calling (Tau2 Telecom 98.7%). It rolls out as Instant, Thinking, and Pro—faster, more structured, and less error‑prone—priced at $1.75/1M input and $14/1M output tokens, with Pro variants supporting xhigh reasoning for top‑quality, end‑to‑end execution.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

GPT-5.2 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GPT-5.2vsLlama 3.1 405BGPT-5.2vsDeepSeek-V2.5GPT-5.2vsClaude Opus 4.6GPT-5.2vsMiMo V2.5 ProGPT-5.2vsGemma 4 26B A4BGPT-5.2vsGrok 4 Fast

Models similar to GPT-5.2

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#30+2.5
OP

GPT-5

OpenAI

71.6 LLMBoard

DetailsCompare
#45-6.1
OP

o1

OpenAI

63.0 LLMBoard

DetailsCompare
#17+6.5
OP

GPT-5.4

OpenAI

75.6 LLMBoard

DetailsCompare
#49-7.6
OP

o3 mini

OpenAI

61.6 LLMBoard

DetailsCompare
#16+7.6
OP

GPT-5.5

OpenAI

76.8 LLMBoard

DetailsCompare
#15+8.1
OP

GPT-5.6-Luna

OpenAI

77.2 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-5.2.

When was GPT-5.2 released?

GPT-5.2's default version was released on Dec 11, 2025.

How much does GPT-5.2 cost?

GPT-5.2's official API price is $1.75 per million input tokens and $14 per million output tokens via OpenAI.

Who created GPT-5.2?

GPT-5.2 is published under OpenAI in the model registry.

What is the context window for GPT-5.2?

The default version has a 400K token context window.

Is GPT-5.2 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer GPT-5.2?

1 published provider offerings are linked to the default version.

What models should I compare GPT-5.2 with?

Nearby ranked alternatives include Llama 3.1 405B, DeepSeek-V2.5, Claude Opus 4.6.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai