OpenAI logo

GPT-5.1 Thinking

Multimodal
OpenAI

GPT-5.1 Thinking is the next iteration of GPT-5 with improved adaptive reasoning capabilities. Unlike GPT-5.1 Instant, GPT-5.1 Thinking more precisely adapts thinking time to each question, providing deeper reasoning for complex queries. The model demonstrates significant improvements in coding and complex reasoning scenarios.

Key Specifications

Parameters
-
Context
256.0K
Release Date
November 11, 2025
Average Score
90.8%

Timeline

Key dates in the model's history
Announcement
November 11, 2025
Today
March 25, 2026

Technical Specifications

Parameters
-
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)
$3.00
Output (per 1M tokens)
$12.00
Max Input Tokens
256.0K
Max Output Tokens
128.0K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Reasoning

Logical reasoning and analysis
GPQA
GPT-5.1 Thinking - GPQA Diamond (without tools)Self-reported
88.0%

Multimodal

Working with images and visual data
MMMU
GPT-5.1 Thinking with tasks level withSelf-reported
85.0%

Other Tests

Specialized benchmarks
TAU2 Telecom
GPT-5.1 Thinking with Benchmark functions ()Self-reported
96.0%
AIME 2025
GPT-5.1 Thinking with (without tools) - AIME 2025 mathematicsSelf-reported
94.0%

License & Metadata

License
proprietary
Announcement Date
November 11, 2025
Last Updated
November 11, 2025

Compare GPT-5.1 Thinking

All comparisons

Similar Models

All Models

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.