Back to Models

GPT-5.4 (xhigh)

GPT-5.4 is OpenAI's flagship frontier model, natively integrating frontier coding (57.7% SWE-bench Pro), state-of-the-art computer-use abilities, and deep agentic workflows over a 1.05M token context window.

Thinking Mode
Parameters
N/A
Context
1,048,576 tokens
Released
May 3, 2026

Leaderboards

Average Score combining domain-specific Autobench scores; Higher is better

Performance vs. Industry Average

Intelligence

GPT-5.4 (xhigh) is of higher intelligence compared to average (2.9), with an intelligence score of 3.1.

Price

GPT-5.4 (xhigh) is more expensive compared to average ($0.75 per 1M Tokens) with a price of $6.33 per 1M Tokens.

Latency

GPT-5.4 (xhigh) has a higher average latency compared to average (44.25s), with an average latency of 131.01s.

P99 Latency

GPT-5.4 (xhigh) has a higher P99 latency compared to average (126.46s), taking 325.77s to receive the first token at P99 (TTFT).

Context Window

GPT-5.4 (xhigh) has a larger context window than average (406k tokens), with a context window of 1049k tokens.

GPT-5.4 (xhigh) - AutoBench