GP

GPT-5.2

Chat modelGPTGPT-5.2

OpenAI GPT-5.2

Release date: 2025-12-11Updated: 2026-06-15 07:18:16.2142,555
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
400K
Chinese support
Supported
Reasoning ability

OpenAI GPT-5.2 is an AI model published by OpenAI, released on 2025-12-11, for Chat model, and 400K context length, under the 不开源 license, with a 100.00 score on AIME2025.

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

GPT-5.2

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Level · Extra-High (Default)Thinking Level · LowThinking Level · MediumThinking Level · High
Context length
400K tokens
Max output length
No data
Model type
Chat model
Modality (in / out)
Text, Image → Text
Release date
2025-12-11
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
GPT-5.2

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
GPT-5.2

Official resources

DataLearnerAI blog
No blog post yet
GPT-5.2

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$1.75/ 1M$14.00/ 1M
Batch
TypeConditionInputOutput
Text-$0.875/ 1M$7.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text5m$1.75/ 1M$0.175/ 1M
GPT-5.2

Benchmark Results

GPT-5.2 currently shows benchmark results led by AIME2025 (1 / 106, score 100), MMMU (1 / 28, score 85.90), GPQA Diamond (8 / 179, score 93.20). 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
Parallel

General Knowledge

19 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Extra-High
92.40
11 / 179
93.20
8 / 179
55.70
41 / 65
ARC-AGI
Medium
72.70
26 / 65
78.70
22 / 65
ARC-AGI
Extra-High
86.20
18 / 65
90.50
15 / 65
MMLU
Extra-High
89.60
11 / 65
LiveBench
Standard Mode
48.91
94 / 115
65.33
53 / 115
LiveBench
Medium
71.84
31 / 115
74.84
19 / 115
9.70
38 / 59
ARC-AGI-2
Medium
26.70
31 / 59
43.30
24 / 59
ARC-AGI-2
Extra-High
52.90
22 / 59
54.20
20 / 59
HLE
Extra-High
34.50
66 / 159
HLE
Extra-HighToolsInternet
45.50
33 / 159

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
Extra-HighTools
80
16 / 108
IC SWE-Lancer(Diamond)
Extra-HighTools
74.60
2 / 8
SWE-Bench Pro - Public
Extra-HighTools
55.60
18 / 44

Math and Reasoning

7 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Extra-High
100
1 / 106
FrontierMath
Extra-HighTools
40.30
8 / 60
6.30
35 / 80
16.70
20 / 80
18.80
16 / 80
18.80
16 / 80
FrontierMath - Tier 4
Extra-HighTools
14.60
23 / 80

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
MMMU
Extra-High
85.90
1 / 28
MMMU
Extra-HighTools
80.40
12 / 28

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
45.80
33 / 63

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Extra-HighTools
98.70
4 / 35
τ²-Bench
Extra-HighTools
82
12 / 40

AI Agent - Information Search

2 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Extra-HighToolsInternet
65.80
24 / 45
BrowseComp
Extra-HighTools
65.80
24 / 45

Productivity Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA
HighTools
70.90
9 / 21
GDPval-AA
Extra-HighTools
61
10 / 21

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
MCP-Atlas
Extra-HighTools
67.60
14 / 23

Compare with other models

GPT-5.2

Publisher

OpenAI GPT-5.2

Model Overview

OpenAI GPT-5.2 is an AI model published by OpenAI, released on 2025-12-11, for Chat model, and 400K context length, under the 不开源 license, with a 100.00 score on AIME2025.

DataLearner on WeChat

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

DataLearner WeChat QR code