GPT-5.1 Codex
GPT-5.1 Codex is a code-tuned variant of GPT-5.1 with a 272,000-token context window, aimed at software development and code-heavy tasks. It handles code generation, refactoring, debugging, and reasoning over large codebases. The model supports function calling and structured outputs, so it integrates with development tools and automated code workflows. Its large context window lets it work across many files and keep changes consistent within a project.
Key info
Input
Output
Features
Context window
272K
Max output
128K
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Global rank#114 of 597 LLMs
TierStrong
Intelligence Index35.6
Math Index95.7
Reasoning & knowledge
MMLU-Pro
86%
GPQA Diamond
86%
Humanity's Last Exam
26%
Long-context reasoning
69%
Coding
LiveCodeBench
85%
SciCode
40%
Agentic & tool use
Terminal-Bench Hard
35%
τ²-Bench Telecom
83%
Math & instruction following
AIME 2025
96%
IFBench
70%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — GPT-5.1 Codex isn't routed through the Opper gateway right now. It may return.
Contact us about this model →