Early preview
O

OpenAI

GPT-5.4

Announced Mar 5, 2026

Reasoning and coding for professional work

01

What could it do?

OpenAI combined recent reasoning and coding advances with document, spreadsheet and tool workflows.

02

What changed?

Brought capabilities from GPT-5.3 Codex into a broader model.

WHY IT MATTERED

Supported work spanning multiple computer applications.

03

Where it fell short

Thinking, Pro and API configurations should not be mixed into one benchmark result.

Sources checked Oct 7, 2026

Release facts were checked against the sources below. Performance claims belong to the developers; we have not independently tested these models.

Developer announcement or release log

Benchmark results

EPOCH AI CAPABILITY ESTIMATE
156.8index points
Tested variant: GPT-5.4Source interval: 155.0 to 158.9Variant date in source: Mar 5, 2026

A benchmark estimate, not a percentage or capability multiplier. Reasoning settings are not specified in this source table. Historical estimates can change in later snapshots.

Epoch AI methodology ↗Download the source snapshotChecked Oct 7, 2026 · CC BY 4.0
PUBLISHED BENCHMARK RESULT
1475rating points
Tested: gpt-5.4-highText Arena Overall · October 8, 2026Reported interval: 1471 to 147964,844 votes

One explicitly named variant per release. Scores come from the same Overall snapshot; preliminary entries and reported intervals are preserved. These are current ratings of earlier variants, not their launch day ratings.

Source: Text Arena ↗Download selected resultsChecked Oct 8, 2026
FOLLOW WHAT HAPPENS NEXT

Breakthroughs, with the followup.

A weekly brief on new discoveries, meaningful checks and what you can actually use.