modelbenchmark.io

GPT-5.2 Pro

OpenAI · gpt-5-2-pro

Compare

Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows

Specification

openai listing

Context
400K
Max output
128K
Released
2025-12-11
Knowledge cutoff
2025-08-31
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · openai list price

Input
$21.00
Output
$168.00

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$10.50
Batch outputopenai$84.00

Batch input is 50% below the interactive input price at the same listing.

Quality

2 benchmarks · 1 source

Composite
87th
percentile of 334 scored models
Rank
43 / 334
±0.13 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
one configuration only
math88th2/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
FrontierMath-Tiers-1-3-v274.0 ±2.6xhighEpoch AI2026-06-13
FrontierMath-Tier-4-v246.0 ±7.8xhighEpoch AI2026-06-13

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 12 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$21.00$168.00
400K
272K
128K
jiekou$18.90$151.20400K128K
poe$19.00$150.00400K128K
azure$21.00$168.00272K128K
edenai$21.00$168.00400K128K
kilo$21.00$168.00400K128K
llmgateway$21.00$168.00400K128K
llmgateway-providers$21.00$168.00400K272K
openrouter$21.00$168.00
400K
272K
128K
orcarouter$21.00$168.00400K128K
vercel$21.00$168.00400K128K
zenmux$21.00$168.00400K128K

More from OpenAI

most-hosted first