Skip to main content

GPT-5.3 Codex (xhigh)

OpenAIGPTProprietary

Description

GPT-5.3-Codex is OpenAI's most capable coding model, combining frontier agentic coding capabilities, improvements in aesthetics, and context compaction. It sets new state-of-the-art results on Terminal-Bench 2.0 (77.3%), OSWorld-Verified (64.7%), and SWE-Lancer IC Diamond (81.4%). First model classified as High capability for cybersecurity under OpenAI's Preparedness Framework. Available in the Codex app and API.

Release Date
2026-02-05
Parameters
Context Length
400K
Modalities
file, image, text

Capability Radar

51
general
53
coding
92
reasoning
68
scienceest.
80
agents
85
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agents & Tools23
67.0
LS
Code Ranking6
91.0
AA
General Ranking13
88.0
AA
Science7
92.0
AA

Benchmark Scores (LLM Stats)

Agents

Terminal-Bench 2.077.3%SR
OSWorld-Verified64.7%SR
SWE-Bench Pro56.8%SR

Code

SWE-Lancer (IC-Diamond subset)81.4%SR

Safety

Cybersecurity CTFs77.6%SR

AA Evaluation Indices

Intelligence Index
53.6
Coding Index
53.1
Gpqa
0.9
Tau2
0.9
Ifbench
0.8
Lcr
0.7
Scicode
0.5
Terminalbench Hard
0.5
Hle
0.4

LLM Stats Category Scores

Tool Calling
80
Safety
80
Agents
70
Code
70
Reasoning
70
Vision
60
General
60
Multimodal
60

Pricing

Input Price$1.75 / 1M tokens
Output Price$14 / 1M tokens
Blended Price (3:1)$4.813 / 1M tokens

Speed

Tokens/sec83.3 tokens/s
Time to First Token58.63s
Time to Answer58.63s

Available Providers

(LS internal units)
ProviderInput PriceOutput Price
OpenAI1.8M14.0M

External Sources