Home/Models/GPT-5.4 Mini
OpenAI logo

GPT-5.4 Mini

by OpenAI · Released Mar 2026

Multimodal
37.3
avg score
Rank #186
Compare
Better than 32% of all models
Context
400K tokens (~200 books)
Input $/1M
$0.75
Output $/1M
$4.50
Type
multimodal
License
Proprietary
Benchmarks
23 tested
Data updated today
About

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

Tested on 23 benchmarks with 38.3% average. Top scores: OTIS Mock AIME 2024-2025 (87.2%), GPQA diamond (78.1%), LiveBench — Coding (74.7%).

Looking for similar performance at lower cost?
GLM 4 32B scores 37.8 (101% as good) at $0.10/1M input · 87% cheaper
Capabilities
coding
50.7
#83 globally
reasoning
38.0
#88 globally
math
35.9
#140 globally
knowledge
40.4
#180 globally
agentic
24.6
#22 globally
speed
70.1
#27 globally
language
30.3
#143 globally
Benchmark Scores
Compare All
Tested on 23 benchmarks · Ranked across 7 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

74.7
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

60.3
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

17.0
ARC-AGI

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

63.7
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

47.4
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

21.9
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

87.2
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

37.0
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Recently Happened
GPT-5.4 Mini joins the OpenAI lineup
Mar 31, 2026
Links
Documentation
Community
BenchGecko API
gpt-5-4-mini
Specifications
  • Typemultimodal
  • Context400K tokens (~200 books)
  • ReleasedMar 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.006
Available On
OpenAI logoOpenAI$0.75
Share & Export
Tweet
GPT-5.4 Mini is a proprietary multimodal AI model by OpenAI, released in March 2026. It has an average benchmark score of 37.3. Context window: 400K tokens.