Skip to content

GPT-5.2 (medium)

ModelActive
by OpenAI · family “gpt-medium”
Epoch Capabilities Index
Not scored by Epoch AI
Released
11 Dec 2025
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (12)

All benchmarks
BenchmarkDomainScorevs best recordedSettingRunSource
Mystery Game Puzzlesgames22.0% ±4.2
26%
medium28 Aug 2026Epoch ↗
Chess Puzzlesgames40.0% ±4.9
56%
medium11 Dec 2025Eval log ↗
Remote Labor Indexagents2.5%
12%
medium—External ↗
SimpleQA Verifiedknowledge32.7% ±1.5
43%
medium27 Aug 2026Eval log ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath16.7% ±5.4
35%
medium11 Dec 2025Epoch ↗
Terminal Benchagents64.9% ±2.8
77%
agent: Droid24 Dec 2025External ↗
ARC-AGI-2reasoning26.7%
28%
medium—External ↗
FrontierMath-2025-02-28-Privatesupersededmath36.9% ±2.8
70%
medium11 Dec 2025Epoch ↗
WeirdMLcoding63.4% ±0.0
68%
medium—External ↗
OTIS Mock AIME 2024-2025math93.9% ±3.1
94%
medium11 Dec 2025Eval log ↗
GPQA diamondscience87.9% ±1.9
92%
medium11 Dec 2025Eval log ↗
ARC-AGIreasoning72.7%
74%
medium—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
This model has no public API price listing

0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 40m ago. Steps show when the price changed.

Events