ModelBeat
Models/GPT-5.1-Codex
All models
O
openai/gpt-5.1-codex

GPT-5.1-Codex is OpenAI’s proprietary AI model, released Nov 12, 2025. It costs $1.25/M input and $10/M output tokens, and handles a 400K-token context window. Its strongest use case is math, where it ranks in the 77th percentile of the models Model Beat tracks.

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.

Context
400K
Input
$1.25 / 1M
Output
$10 / 1M
Released
Nov 12, 2025
Modalities
textimagetext
Strongest atMath top 23%Reasoning & Knowledge top 40%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where GPT-5.1-Codex lands among all models tracked on Model Beat.

60.0
Intelligence Index
Epoch AI
60th percentile of tracked models
51.0
Coding Index
Epoch AI
51st percentile of tracked models
52.0
Agentic Index
Epoch AI
52nd percentile of tracked models

Reasoning

3 evals
GPQA Diamond86.0%

Graduate-level scientific reasoning

Humanity's Last Exam23.4%

Frontier of human expert knowledge

MMLU-Pro86.0%

Broad expert knowledge

Coding

3 evals
LiveCodeBench84.9%

Contamination-free coding

SciCode40.2%

Scientific research coding

WebDev Arena1331

Human-rated web development

Math

1 evals
AIME 2024/202595.7%

Olympiad-qualifier math

Agentic & Tools

3 evals
APEX20.6%

Multi-step agentic tasks

Terminal-Bench57.8%

Command-line agentic tasks

τ²-bench83.0%

Tool-agent-user reliability

In the news

2

Compare GPT-5.1-Codex with

Frequently asked questions

What is GPT-5.1-Codex?

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.

Who created GPT-5.1-Codex?

GPT-5.1-Codex is an AI model developed by OpenAI, part of the GPT family, released Nov 12, 2025.

How much does GPT-5.1-Codex cost?

GPT-5.1-Codex is served from $1.25 per million input tokens and $10 per million output tokens (cheapest credible provider on OpenRouter: Azure).

What is GPT-5.1-Codex's context window?

GPT-5.1-Codex supports a context window of up to 400K tokens.

How does GPT-5.1-Codex perform on benchmarks?

On standardized evaluations tracked by Epoch AI, GPT-5.1-Codex scores 84.9% on LiveCodeBench, 86.0% on MMLU-Pro, 95.7% on AIME 2024/2025.

Is GPT-5.1-Codex open source?

GPT-5.1-Codex is a proprietary model (API access), available through its provider's API rather than as a downloadable open-weight model.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Jul 30, 2026.