Top 4% of all models
Context
128K tokens (~64 books)
Input $/1M
$1.25
Output $/1M
$10.00
Type
multimodal
License
Proprietary
Benchmarks
7 tested
Data updated today
About
GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.
Tested on 7 benchmarks with 81.9% average. Top scores: Chatbot Arena Elo — Overall (1426.0%), Aider polyglot (88.0%), HELM — IFEval (87.5%).
Looking for similar performance at lower cost?
Step 3.5 Flash scores 89.5 (101% as good) at $0.10/1M input · 92% cheaper
Step 3.5 Flash scores 89.5 (101% as good) at $0.10/1M input · 92% cheaper
Capabilities
coding
88.0
#1 globally
reasoning
85.7
#2 globally
math
64.7
#40 globally
knowledge
82.7
#4 globally
language
87.5
#23 globally
Benchmark Scores
Compare AllTested on 7 benchmarks · Ranked across 6 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
codingCompare coding →
Aider polyglot
88.0—Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
reasoningCompare reasoning →
HELM — WildBench
85.7—Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.
mathCompare math →
HELM — Omni-MATH
64.7—Stanford HELM evaluation of mathematical reasoning across diverse problem types.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
BenchGecko API
gpt-5-chat
Specifications
- Typemultimodal
- Context128K tokens (~64 books)
- ReleasedAug 2025
- LicenseProprietary
- StatusActive
- Cost / Message~$0.013
Available On
Learn More
Share & Export
Frequently Asked Questions
GPT-5 Chat is a proprietary multimodal AI model by OpenAI, released in August 2025. It has an average benchmark score of 89.0. Context window: 128K tokens.