Coding-focused GPT-5.2 variant with optimized routing.
Added Jan 14, 2026
Context Window
400.0K
Max Output
128.0K
Avg output tokens (7d)
36 tokens
Input Price (Auto)
$1.75/1M
Output Price (Auto)
$14.00/1M
Cache Read (Auto)
$0.18/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
33.0
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
89.9%
Better than 89% of models compared
HLE
Humanity's Last Exam
35.7%
Better than 87% of models compared
IFBench
Instruction-following benchmark
77.6%
Better than 96% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
92.1%
Better than 87% of models compared
AA-LCR
Long context reasoning evaluation
82.3%
Better than 96% of models compared
CritPt
Research-level physics reasoning
8.7%
Coding
Terminal-Bench Hard
Agentic coding and terminal use
37.1%
Better than 84% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
41.1%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
73.4%
Last updated Sep 7, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare GPT 5.2 Codex with similar models from the same provider or model family.
GPT 5.3 Codex
openai/gpt-5.3-codexCoding-focused GPT-5.3 variant with optimized routing.
GPT 5.1 Codex Max
openai/gpt-5.1-codex-maxTop-tier GPT-5.1 Codex route used when direct OpenAI is unavailable.
GPT 5.1 Codex
openai/gpt-5.1-codexCoding-focused GPT-5.1 variant with optimized routing.
GPT 5.1 Codex Mini
openai/gpt-5.1-codex-miniLightweight GPT-5.1 Codex path.
GPT 6 Astra Pro
openai/gpt-6-astra-proGPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.
GPT 6 Astra
openai/gpt-6-astraOpenAI's most capable model for the hardest end-to-end work, with state-of-the-art performance in computer use, browsing, software engineering, science, and professional tasks. Astra is designed to carry long, multistep workflows across code, browsers, and professional software through to a finished result.