TAU2
Measured May 14, 2026Source
Score
0.87
Models15 1 
GPT-5 Codex (high)
OpenAIOpenAIUnited States
GPT-5 Codex (high) is a high-performance model from OpenAI's Codex series, optimized for advanced code generation, understanding, and complex reasoning tasks. It is designed to handle sophisticated programming challenges with high accuracy and efficiency.
CodingReasoning
Input / 1M tokens
$1.25Output / 1M tokens
$10.00Output tokens/s
179.44First-token seconds
9.04sSupported plans
4Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.38
Lcr
Measured May 14, 2026Source
Score
0.69
Ifbench
Measured May 14, 2026Source
Score
0.74
Aime 25
Measured May 14, 2026Source
Score
0.99
Scicode
Measured May 14, 2026Source
Score
0.41
Livecodebench
Measured May 14, 2026Source
Score
0.84
Hle
Measured May 14, 2026Source
Score
0.26
Gpqa
Measured May 14, 2026Source
Score
0.84
Mmlu Pro
Measured May 14, 2026Source
Score
0.87
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
98.7
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
38.9
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
44.6
Aime
Measured May 14, 2026Source
Score
0.96
Math 500
Measured May 14, 2026Source
Score
0.99
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