Skip to content
llmwaves

GPT-5.4 (batch)

OpenAI · released Mar 5, 2026

ProprietaryReasoningTool useStructured outputVisionBatch endpoint

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

Specification

Context window
1.05M
Max output
128K
Knowledge cutoff
Not stated
Parameters
Undisclosed
Licence
Proprietary
Serving providers
1
Moderated
Yes

Intelligence

53.1

97th percentile

Coding

71.1

Coding Index

Agentic

44.2

Agentic Index

Output speed

Median across providers

Latency

Time to first token

Cost per task

$0.66

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • GPQA Diamond
    92.0%
  • τ²-bench (Telecom)
    87.1%
  • AA-LCR (long context)
    77.7%
  • IFBench
    73.9%
  • Terminal-Bench Hard
    57.6%
  • SciCode
    56.6%
  • Humanity's Last Exam
    43.7%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
GPQA Diamond92.0%
τ²-bench (Telecom)87.1%
AA-LCR (long context)77.7%
IFBench73.9%
Terminal-Bench Hard57.6%
SciCode56.6%
Humanity's Last Exam43.7%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Muse Spark 1.153.2
GPT-5.4 (batch)53.1
GPT-5.453.1
GLM 5.252.6
GPT-5.6 Luna52.3
Gemini 3.5 Flash52.0
V4 Flash 073151.8
V4 Flash 042351.8

Percentile among all indexed models

Intelligence97th
Coding89th
Agentic77th
Terminal work97th
Arena Elo72th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$1.25
Output / 1M tokens
$7.5
Cached input / 1M
$0.125
Blended 3:1
$2.81

One task, estimated

$0.66

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,250
Win rate
63.6%
Strongest at
UI components
Tournaments
129

Elo by category

Dot position on a 1,050–1,250 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
UI components125063.6%
Game development123653.6%
Data visualisation122352.2%
Websites122150.8%
SVG118853.2%
3D scenes112039.0%
Mobile apps114745.9%
Full-stack apps105940.8%