GPT-5.1 is an AI model published by OpenAI, released on 2025-11-12, for Reasoning model, and 400K context length, with a 1387.00 score on Text Arena (Coding).
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $1.25/ 1M tokens | $10.00/ 1M tokens |
| Image | - | $1.25/ 1M tokens | — |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $0.625/ 1M tokens | $5.00/ 1M tokens |
| Image | - | $0.625/ 1M tokens | — |
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | - | $0.0000/ 1M tokens Cache = write | — |
| Text | - | $0.0000/ 1M tokens | $0.125/ 1M tokens |
| Text | - | — | $0.125/ 1M tokens Cache = hit |
| Image | - | $0.0000/ 1M tokens Cache = write | — |
| Image | - | — | $0.125/ 1M tokens Cache = hit |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
Benchmark Results
GPT-5.1 currently shows benchmark results led by MMMU (2 / 28, score 85.40), Terminal Bench Hard (2 / 13, score 43), FrontierMath (13 / 60, score 26.70). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
General Knowledge
13 evaluationsGeneral Evaluation
2 evaluationsCoding and Software Engineer
8 evaluationsMath and Reasoning
5 evaluationsMultimodal Understanding
3 evaluationsAgent Level Benchmark
2 evaluationsAI Agent - Tool Usage
2 evaluationsCompare with other models
Publisher
Model Overview
GPT-5.1 is an AI model published by OpenAI, released on 2025-11-12, for Reasoning model, and 400K context length, with a 1387.00 score on Text Arena (Coding).
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
