01Overview02Models03Rankings04Compare05Quiz06Guide

Model

GPT-5.4 NO.13

Previous-generation balanced workhorse, succeeded by GPT-5.6 Terra.

CompareBack to the index

OpenAI · GPT · Balanced · Closed weights

Specification

Fig.01 — GPT — OpenAI

USA

Context window
1.1Mtokens
Max output
128Ktokens
Input price
$2.50/ 1M
Output price
$15/ 1M
Cached input
$0.25/ 1M
Throughput
—
Class
Balanced
Modalities
Text, Image, Pdf
Weights
Closed
Knowledge cutoff
Oct 2025
Released
Mar 2026

Overview

GPT-5.4 was OpenAI's balanced workhorse before GPT-5.6 Terra, delivering near-flagship reasoning and coding at half the per-token cost of the GPT-5.5 flagship. It retains genuinely reliable agentic behavior and a roughly 1M-token context with full multimodal input, and remains a fine choice for teams already on it — though GPT-5.6 Terra now offers GPT-5.5-class quality at the same price point.

Strengths

  • Strong, reliable all-round reasoning and coding
  • Half the price of the flagship
  • Roughly 1M-token context window
  • Multimodal text, image, and PDF input
  • Good balance of speed and quality

Trade-offs

  • Trails GPT-5.5 on the hardest tasks
  • Pricier than mini/nano for bulk work
  • Long-context premium applies above 272K tokens

Fit

Best for

  • General-purpose production assistants
  • Everyday coding and refactoring
  • Document analysis and summarization
  • Agentic tasks on a budget
  • RAG over large corpora

Not ideal for

  • Absolute frontier reasoning (use GPT-5.5 Pro)
  • Ultra-cheap high-volume classification (use nano)

Capabilities

Ten axes, normalized 0–100 and scored the same way across the whole catalog — so a 78 here means what a 78 means anywhere else on the bench.

Fig.02 — Capability radar

0 — 100

Reasoning
90
Coding
90
Math
90
Writing
88
Knowledge
90
Speed
62
Agentic
88
Vision
87
Multilingual
88
Long Context
88

Benchmarks

Public results, with independent third-party runs marked. Bars normalize percentages against 100 and Elo ratings against a 1500 ceiling.

Independent index

Artificial Analysis Intelligence Index

Composite of ~9–10 independent evals · Artificial Analysis

51/ 100

BenchmarkResult
Artificial Analysis Intelligence IndexIndependentGeneral · Artificial Analysis
51%
SWE-bench VerifiedIndependentCoding · SWE-bench
76.9%
SWE-bench ProIndependentCoding · SWE-bench Pro
59.1%
τ-benchIndependentAgentic · τ-bench
78.3%
GPQA DiamondIndependentReasoning · Independent aggregators
88.4%
LiveBenchIndependentGeneral · LiveBench
80.3%
Terminal-Bench HardIndependentAgentic · Artificial Analysis
57.6%
DeepSWEIndependentCoding · Datacurve
56%
LMArena EloIndependentGeneral · LMArena
1495Elo

Alternatives

Models in roughly the same class — the ones worth weighing against this record.

Compare side by side
01GPT-5.6 TerraOpenAIThe GPT-5.6 balanced workhorse — GPT-5.5-class quality at half the price.02Gemini 3.5 FlashGoogle DeepMindFast, cheap multimodal workhorse with near-Pro quality.03Claude Sonnet 4.6AnthropicThe production workhorse — best balance of speed and intelligence.

Index

PreviousGPT-5.5 ProNextGPT-5.4 mini
All models/EDUCATION