Skip to content

GPT-5.2

ModelActive
by OpenAI · family “gpt”

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly... (description from the OpenRouter listing)

in: filein: imagein: textout: textReasoningTool useStructured output
Epoch Capabilities Index
153.4 #36 of 268
90% CI 151.7 – 155.2
Listing ↗
Released
11 Dec 2025
Context window
400K tokens
Max output
128K tokens
Input $ / 1M tokens
$1.75
Output $ / 1M tokens
$14.0
Cached input $ / 1M
$0.17
Each benchmark shown separately with its own source

Benchmark results (15)

BenchmarkDomainScorevs best recordedSettingRunSource
Mystery Game Puzzlesgames23.0% ±4.2
27%
high6 Aug 2026Epoch ↗
CL-benchlong-context18.1%
65%
high—External ↗
Chess Puzzlesgames40.0% ±4.9
56%
high11 Dec 2025Eval log ↗
SimpleQA Verifiedknowledge34.3% ±1.5
45%
high27 Aug 2026Eval log ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath18.8% ±5.6
39%
high11 Dec 2025Epoch ↗
GSO-Benchcoding27.5%
58%
high—External ↗
ARC-AGI-2reasoning43.3%
46%
high—External ↗
METR Time Horizonsagents75.3%
88%
high—External ↗
FrontierMath-2025-02-28-Privatesupersededmath40.3% ±2.9
77%
high11 Dec 2025Epoch ↗
VPCTmultimodal67.0%
74%
high—External ↗
OTIS Mock AIME 2024-2025math96.1% ±2.6
96%
high11 Dec 2025Eval log ↗
SimpleBenchreasoning45.8%
56%
high—External ↗
SWE-Bench verifiedcoding73.8% ±2.0
88%
high12 Feb 2026Eval log ↗
GPQA diamondscience88.2% ±1.9
92%
high11 Dec 2025Eval log ↗
ARC-AGIreasoning78.7%
80%
high—External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

10 recorded prices on 7 Jan 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.

Events