GPT-5.2 Codex (Xhigh)
OpenAIGPTProprietary
Description
GPT-5.2 Codex is a version of GPT-5.2 optimized for agentic coding tasks in Codex or similar environments. It features higher reasoning capabilities and is available in the Responses API. The underlying model snapshot is regularly updated.
Release Date
2025-12-11
Parameters
—
Context Length
400K
Modalities
image, text
Capability Radar
60
general
60
coding
70
reasoning
60
scienceest.
60
agents
85
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Math Reasoning | 32 | 89.0 | LB |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Math
LiveBench
74.3%
Reasoning
Terminal-Bench 2.0Stanford × Laude Institute (2026)
64.0%SR
SWE-Bench ProPrinceton NLP (2024)
56.4%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Math70
Reasoning60
General60
Agents60
Code60
Tool Calling60
Pricing
Input Price$1.75 / 1M tokens
Output Price$14 / 1M tokens
Blended Price (3:1)$4.8125 / 1M tokens
Cache Read Price$0.175 / 1M tokens
Speed
Tokens/sec114.3
Time to First Token69.29s
Time to Answer69.29s
Provider Price Ranking
Provider Price Ranking
10 providers
Cheapest: PoeMost Expensive: Impossibl
ProviderInputOutput
1PoeCheapest
$1.6
$13
2OpenAIPRIMARY
$1.75
$14
3NanoGPT
$1.75
$14
4OpenRouter
$1.75
$14
5ZenMux
$1.75
$14
6Kilo Gateway
$1.75
$14
7Vercel AI Gateway
$1.75
$14
8OrcaRouter
$1.75
$14
9Ofox
$1.75
$14
10Impossibl
$1.75
$14
Compare pricing across different API providers for this model.