DataLearner logo
GP

GPT-5.1

Reasoning modelGPTGPT-5.1

GPT-5.1

Release date: 2025-11-12Updated: 2026-06-15 07:18:15.4151,010
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
400K
Chinese support
Supported
Reasoning ability

GPT-5.1 is an AI model published by OpenAI, released on 2025-11-12, for Reasoning model, and 400K context length, with a 95.60 score on τ²-Bench - Telecom.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GPT-5.1

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
400K tokens
Max output length
128K tokens
Model type
Reasoning model
Modality (in / out)
Text, Image → Text
Release date
2025-11-12
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
GPT-5.1

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
GPT-5.1

Official resources

Paper
DataLearnerAI blog
GPT-5.1

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$1.25/ 1M$10.00/ 1M
Batch
TypeConditionInputOutput
Text-$0.625/ 1M$5.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-$0.0000/ 1M$0.125/ 1M
GPT-5.1

Benchmark Results

GPT-5.1 currently shows benchmark results led by MMMU (2 / 29, score 85.40), Terminal Bench Hard (2 / 13, score 43), GPQA Diamond (31 / 187, score 88.10). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage
Internet

General Knowledge

16 evaluations
Benchmark / mode
Score
Rank/total
88.10
31 / 187
88.10
31 / 187
88.10
31 / 187
72.80
28 / 68
57.70
40 / 68
33.20
53 / 68
LiveBench
Standard Mode
42.65
106 / 115
59.95
71 / 115
LiveBench
Medium
69.17
41 / 115
72.04
29 / 115
26.50
97 / 172
HLE
High
25.70
100 / 172
HLE
HighToolsInternet
42.70
54 / 172
17.60
36 / 62
6.50
44 / 62
1.90
53 / 62

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
76.30
34 / 112
76.30
34 / 112
50.80
40 / 54

Math and Reasoning

6 evaluations
Benchmark / mode
Score
Rank/total
94
28 / 107
94
28 / 107
FrontierMath
HighTools
26.70
13 / 60
4.20
40 / 80
12.50
29 / 80
12.50
29 / 80

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
85.40
2 / 29
MMMU
High
85.40
2 / 29

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
53.20
23 / 63

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
95.60
14 / 35
43
2 / 13

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
50.80
43 / 53

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
HighTools
50.10
25 / 27
47.60
38 / 47

Compare with other models

GPT-5.1

Publisher

GPT-5.1

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 95.60 score on τ²-Bench - Telecom.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code