GPT-5.1

Name: GPT-5.1
Author: OpenAI

Multimodal

OpenAI

GPT-5.1 is OpenAI's flagship model for coding and agentic tasks with configurable reasoning and non-reasoning effort. It delivers strong results across competition mathematics, function calling, long-context browsing, and software engineering benchmarks.

Key Specifications

Parameters

Context

400.0K

Release Date

November 13, 2025

Average Score

77.9%

API Documentation Research Paper Results Blog

Timeline

Key dates in the model's history

Announcement

November 13, 2025

Today

August 27, 2026

Technical Specifications

Parameters

Training Tokens

Knowledge Cutoff

September 30, 2024

Family

Capabilities

MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)

$1.25

Output (per 1M tokens)

$10.00

Max Input Tokens

400.0K

Max Output Tokens

128.0K

Supported Features

Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests

SWE-Bench Verified

GPT-5.1 with adaptive reasoning - SWE-bench Verified (all 500 problems). • Self-reported

76.3%

Reasoning

Logical reasoning and analysis

GPQA

GPT-5.1 - GPQA Diamond (no tools). • Self-reported

88.1%

Multimodal

Working with images and visual data

MMMU

GPT-5.1 with adaptive reasoning - College-level visual problem-solving with multimodal reasoning. • Self-reported

85.4%

Other Tests

Specialized benchmarks

AIME 2025

GPT-5.1 with adaptive reasoning (no tools) - AIME 2025 competition mathematics. • Self-reported

94.0%

BrowseComp Long Context 128k

GPT-5.1 with adaptive reasoning - BrowseComp long-context 128k variant. • Self-reported

90.0%

FrontierMath

GPT-5.1 with adaptive reasoning (with Python tool) - FrontierMath Tier 1-3 expert-level mathematics. • Self-reported

26.7%

Tau2 Airline

GPT-5.1 with adaptive reasoning - Function calling benchmark (airline domain). • Self-reported

67.0%

Tau2 Retail

GPT-5.1 with adaptive reasoning - Function calling benchmark (retail domain). • Self-reported

77.9%

Tau2 Telecom

GPT-5.1 with adaptive reasoning - Function calling benchmark (telecom domain). • Self-reported

95.6%

License & Metadata

License

proprietary

Announcement Date

November 13, 2025

Last Updated

August 27, 2026

Similar Models

All Models

GPT-4o mini

OpenAI

Best score:0.9 (HumanEval)

Released:Jul 2024

Price:$0.15/1M tokens

o3

OpenAI

Best score:0.8 (GPQA)

Released:Apr 2025

Price:$2.00/1M tokens

GPT-4.5

OpenAI

Best score:0.9 (MMLU)

Released:Feb 2025

Price:$75.00/1M tokens

GPT-5 nano

OpenAI

Best score:0.7 (GPQA)

Released:Aug 2025

Price:$0.05/1M tokens

o1-pro

OpenAI

Best score:0.8 (GPQA)

Released:Dec 2024

GPT-4

OpenAI

Best score:1.0 (ARC)

Released:Jun 2023

Price:$30.00/1M tokens

GPT-4o

OpenAI

Best score:0.9 (HumanEval)

Released:May 2024

Price:$2.50/1M tokens

GPT-5 mini

OpenAI

Best score:0.8 (GPQA)

Released:Aug 2025

Price:$0.25/1M tokens

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.