GPT‑5.3‑Codex is OpenAI’s most capable agentic coding model, designed to handle not just code generation but longer, end‑to‑end work on a computer. It combines the frontier coding strength of GPT‑5.2‑Codex with the reasoning and professional knowledge capabilities of GPT‑5.2, and is engineered to run faster (about 25% faster in Codex). It’s built for long‑running, multi‑step tasks that can include research, tool use, debugging, and complex execution, while staying interactive—so you can steer it, ask questions, and refine direction as it works without losing context. In evaluations, it sets new highs on software engineering and agentic benchmarks (including SWE‑Bench Pro and Terminal‑Bench 2.0) and shows strong results on OSWorld‑Verified and GDPval. It’s also deployed with strengthened cybersecurity safeguards and is trained to help identify software vulnerabilities.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference.
Uptime
24hoursDirect request success rate on AI Gateway and per-provider.
Throughput
24hoursP50 throughput on live AI Gateway traffic, in tokens per second (TPS).
Latency
24hoursP50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.
Activity
Token volume and request traffic to this model over time.
Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis
Artificial Analysis
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All
Related Models
More models from OpenAI