GPT 5.3 Codex
Release Date: 2/24/2026
Benchmarked by 
GPT-5.3-Codex is OpenAI's frontier agentic coding model designed for long-running, detailed software engineering tasks.
Accuracy (Average)
62.36%
Latency (Average)
1869.81s
Avg. Cost (In/Out)
1.75 / 14
Context Window
400k
Max Output Tokens
128k
Input Modality
Hyperparameter settings
Default Provider :
OpenAI
Some benchmarks may use different provider and parameters. Please refer to the benchmark page for more information.
Temperature
Default
Top P
Default
Top K
Default
Max Output Tokens
128,000
Reasoning Effort
xhigh
Benchmarks
Accuracy
Rankings
Academic Benchmarks
Proprietary Benchmarks (contact us to get access)