GPT-5.4 — OpenAI | Modeldex

GPT-5.4

Active59.3Competent

OpenAI GPT-5.4.

Updated 4 days agoStructured data from Modeldex catalog

VisionAgenticLong context

API release

Mar 5, 2026(last month)

Intelligence Index

59.3/ 100

Competentweighted across 5 benchmarks

Factual grounding: 91.9
Reasoning: 77.3
Long context: 42.1
Medical: 26.0

Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.

History

GPT-5.4 became available via the OpenAI API on 2026-03-05.

Training & availability

OpenAI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 1.1M tokens.
Max output: 128K tokens.
Input modalities: text, image.

Recommended for: vision, agentic, long-context.

Quick start

Minimal example using the openai API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(api_key="sk-...")
resp = client.chat.completions.create(
    model="gpt-5-4",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Benchmarks

Benchmark	Score	Source
FACTS GroundingFactual grounding	91.86%	Third-party llm-stats.com
GPQA DiamondReasoning	77.27% accuracy	Third-party llm-stats.com
HealthBenchMedical	26.04%	Third-party llm-stats.com

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Strong benchmark performance

Top-tier benchmarks. Pricing not publicly available — check the provider.

Quality percentile: 78%
Effective price: —
Pricing breakdown: — in
— out

Community ratings

No ratings yet. Be the first to rate GPT-5.4.