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
46
general
45
coding
90
reasoning
66
scienceest.
60
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agents & Tools | 40 | 61.0 | LS |
| Code Ranking | 32 | 77.0 | AA |
| General Ranking | 20 | 87.0 | AA |
| Science | 14 | 87.0 | AA |
Benchmark Scores (LLM Stats)
Agents
Terminal-Bench 2.0
64.0%SR
SWE-Bench Pro
56.4%SR
AA Evaluation Indices
Intelligence Index49.0
Coding Index43.0
Tau20.9
Gpqa0.9
Ifbench0.8
Lcr0.8
Scicode0.5
Terminalbench Hard0.4
Hle0.3
LLM Stats Category Scores
Tool Calling60
Agents60
Code60
Reasoning60
Pricing
Input Price$1.75 / 1M tokens
Output Price$14 / 1M tokens
Blended Price (3:1)$4.813 / 1M tokens
Speed
Tokens/sec99.0 tokens/s
Time to First Token1.54s
Time to Answer1.54s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| OpenAI | 1.8M | 14.0M |