OpenAIGPT-5v5.4

GPT-5.4

No ratings yet

Be the first to review this model

OpenAI's latest flagship model released March 2026, featuring Thinking and Pro variants. Sets new benchmarks across reasoning, coding, and creative tasks.

Released

March 5, 2026

Parameters

Unknown

Context

Pricing

Paid

Benchmark Performance

Benchmark	Category	Score	Performance
MMLU	knowledge	91.0%	91
HumanEval	coding	85.1%	85
MATH	reasoning	88.6%	89
Chatbot Arena ELO	overall	1479	97

Last updated: March 15, 2026

Benchmark scores may vary based on evaluation methodology and conditions.

Reviews(0)

No reviews yet

Be the first to share your experience with GPT-5.4.