TAU2
Measured May 14, 2026Source
Score
0.92
Models13 1 
GPT-5.2 Codex (xhigh)
OpenAIOpenAIUnited States
GPT-5.2 Codex (xhigh) is a high-performance model from OpenAI's Codex series, specialized in advanced code generation, understanding, and transformation tasks. It is optimized for complex programming challenges and likely features enhanced reasoning capabilities for technical domains.
CodingReasoningFast
Input / 1M tokens
$1.75Output / 1M tokens
$14.00Output tokens/s
91.36First-token seconds
2.18sSupported plans
4Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.37
Lcr
Measured May 14, 2026Source
Score
0.76
Ifbench
Measured May 14, 2026Source
Score
0.78
Scicode
Measured May 14, 2026Source
Score
0.55
Hle
Measured May 14, 2026Source
Score
0.34
Gpqa
Measured May 14, 2026Source
Score
0.9
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
43
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
49
Aime 25
Measured May 14, 2026Source
Score
0.99
Livecodebench
Measured May 14, 2026Source
Score
0.89
Mmlu Pro
Measured May 14, 2026Source
Score
0.87
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
99
Plan availability
Products and plans that support this model
Apertis Coding Plan
Apertis Coding Plan
Apertis Coding Plan is a subscription-based AI coding service providing unified access to 30+ AI models (GPT-5.4, Claude Opus 4.6, Gemini 3.1 Pro, and more) through a single API key. Designed for developers using coding agents like Claude Code, Cursor, Cline, and OpenCode, it offers predictable monthly pricing, free prompt caching, auto-failover, and quota-based billing across OpenAI, Anthropic, Google, and other providers.
Discussion
Thinking... Make sure you are connected to GitHub server