TAU2
Measured May 14, 2026Source
Score
0.85
Models13 0 
GPT-5.2 (xhigh)
OpenAIOpenAIUnited States
GPT-5.2 (xhigh) is a high-performance variant of OpenAI's GPT-5 series, offering enhanced reasoning, multimodal understanding, and long-context capabilities. It is designed for complex, high-stakes tasks requiring deep analysis and synthesis across text and images.
ReasoningCodingMultimodalLong context
Input / 1M tokens
$1.75Output / 1M tokens
$14.00Output tokens/s
66.76First-token seconds
60.09sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.47
Lcr
Measured May 14, 2026Source
Score
0.73
Ifbench
Measured May 14, 2026Source
Score
0.75
Aime 25
Measured May 14, 2026Source
Score
0.99
Scicode
Measured May 14, 2026Source
Score
0.52
Livecodebench
Measured May 14, 2026Source
Score
0.89
Hle
Measured May 14, 2026Source
Score
0.35
Gpqa
Measured May 14, 2026Source
Score
0.9
Mmlu Pro
Measured May 14, 2026Source
Score
0.87
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
99
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
48.7
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
51.3
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server