Home/Models/GPT-5.4 Pro
OpenAI logo

GPT-5.4 Pro

by OpenAI · Released Mar 2026

Multimodal1M Context
93.0
avg score
Rank #5
Compare
Top 2% of all models
Context
1.1M tokens (~525 books)
Input $/1M
$30.00
Output $/1M
$180.00
Type
multimodal
License
Proprietary
Benchmarks
8 tested
Data updated today
About

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

Tested on 8 benchmarks with 66.7% average. Top scores: ARC-AGI (94.5%), GPQA diamond (92.8%), ARC-AGI-2 (83.3%).

Looking for similar performance at lower cost?
Step 3.5 Flash scores 89.5 (96% as good) at $0.10/1M input · 100% cheaper
Capabilities
reasoning
82.3
#6 globally
math
43.8
#97 globally
knowledge
66.4
#29 globally
Benchmark Scores
Compare All
Tested on 8 benchmarks · Ranked across 3 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

94.5
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

83.3
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

68.9
FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

50.0
FrontierMath-Tier-4-2025-07-01-Private

Hardest tier of FrontierMath. Problems at the frontier of human mathematical ability, many unsolved by most mathematicians.

37.5
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

92.8
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

58.6
SimpleQA Verified

Simple factual questions with verified correct answers. Tests accuracy of basic knowledge retrieval. Low scores indicate hallucination.

47.8
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Recently Happened
GPT-5.4 Pro launched · OpenAI's new flagship
Mar 14, 2026
Links
Documentation
Community
BenchGecko API
gpt-5-4-pro
Specifications
  • Typemultimodal
  • Context1.1M tokens (~525 books)
  • ReleasedMar 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.240
Available On
OpenAI logoOpenAI$30.00
Share & Export
Tweet
GPT-5.4 Pro is a proprietary multimodal AI model by OpenAI, released in March 2026. It has an average benchmark score of 93.0. Context window: 1M tokens.