GP

GPT-5-Nano

Reasoning modelGPT NanoGPT-5

GPT-5-Nano

Release date: 2025-08-07Updated: 2026-06-15 07:18:14.9511,192
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
256K
Chinese support
Supported
Reasoning ability

GPT-5-Nano is an AI model published by OpenAI, released on 2025-08-07, for Reasoning model, and 256K context length, under the 不开源 license, with a 78.30 score on DocVQA.

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

GPT-5-Nano

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
256K tokens
Max output length
4K tokens
Model type
Reasoning model
Modality (in / out)
Text, Image → Text
Release date
2025-08-07
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
GPT-5-Nano

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
GPT-5-Nano

Official resources

Paper
No paper available
DataLearnerAI blog
No blog post yet
GPT-5-Nano

API details

API speed
No data
No public API pricing yet.
GPT-5-Nano

Benchmark Results

GPT-5-Nano currently shows benchmark results led by FrontierMath (31 / 60, score 8.30), FrontierMath - Tier 4 (56 / 80, score 2.10), LiveBench (97 / 115, score 48.62). 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

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
78.30
5 / 5
57.60
28 / 28

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
8.30
31 / 60
7.20
33 / 60
2.10
56 / 80

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
LiveBench
Standard Mode
48.56
98 / 115
34.34
113 / 115
48.62
97 / 115

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
68.80
33 / 37

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

GPT-5-Nano

Publisher

GPT-5-Nano

Model Overview

GPT-5-Nano is an AI model published by OpenAI, released on 2025-08-07, for Reasoning model, and 256K context length, under the 不开源 license, with a 78.30 score on DocVQA.

DataLearner on WeChat

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

DataLearner WeChat QR code