Home/Models/GPT-4.5
OpenAI logo

GPT-4.5

by OpenAI · Released Jan 2024

35.2
avg score
Rank #164
Compare
Better than 30% of all models
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text
License
Proprietary
Benchmarks
13 tested
Data updated today
About

Tested on 13 benchmarks with 35.9% average. Top scores: MATH level 5 (78.6%), Lech Mazur Writing (75.6%), Fiction.LiveBench (63.9%).

Capabilities
coding
33.9
#110 globally
reasoning
10.8
#131 globally
math
58.2
#53 globally
knowledge
43.2
#132 globally
Benchmark Scores
Compare All
Tested on 13 benchmarks · Ranked across 4 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

44.9
WeirdML

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

39.4
Cybench

Capture-the-flag cybersecurity challenges. Tests vulnerability analysis, reverse engineering, cryptography, and exploitation skills.

17.5
SimpleBench

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

21.4
ARC-AGI

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

10.3
ARC-AGI-2

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

0.8
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

78.6
OTIS Mock AIME 2024-2025

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

37.7
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
gpt-4-5
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseProprietary
  • Statusbenchmark-only
Available On
OpenAI logoOpenAITBD
Share & Export
Tweet
GPT-4.5 is a proprietary text AI model by OpenAI, released in January 2024. It has an average benchmark score of 35.2.