GP

GPT-5-mini

Foundation modelGPT MiniGPT-5

GPT-5-mini

Release date: 2025-08-07Updated: 2026-06-15 07:18:15.1162,344
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
400K
Chinese support
Supported
Reasoning ability

GPT-5-mini is an AI model published by OpenAI, released on 2025-08-07, for Foundation model, and 400K context length, under the 不开源 license, with a 1200.00 score on CodeClash.

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

GPT-5-mini

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
400K tokens
Max output length
128K tokens
Model type
Foundation 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-mini

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-mini

Official resources

GPT-5-mini

API details

API speed
3/5
No public API pricing yet.
GPT-5-mini

Benchmark Results

GPT-5-mini currently shows benchmark results led by FrontierMath (18 / 60, score 19.30), FrontierMath - Tier 4 (35 / 80, score 6.30), LiveBench (51 / 115, score 65.91). 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

General Knowledge

8 evaluations
Benchmark / mode
Score
Rank/total
78
69 / 126
69
119 / 179
0
177 / 179
LiveBench
Standard Mode
61
66 / 115
53.07
85 / 115
65.91
51 / 115
5
155 / 159
0
159 / 159

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
CodeClash
Standard ModeTools
1200
5 / 8
55
84 / 120

Math and Reasoning

6 evaluations
Benchmark / mode
Score
Rank/total
47
90 / 106
47
90 / 106
19.30
18 / 60
19
20 / 60
4.20
40 / 80
6.30
35 / 80

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
80.30
23 / 37

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

GPT-5-mini

Publisher

GPT-5-mini

Model Overview

GPT-5-mini is an AI model published by OpenAI, released on 2025-08-07, for Foundation model, and 400K context length, under the 不开源 license, with a 1200.00 score on CodeClash.

DataLearner on WeChat

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

DataLearner WeChat QR code