ChatGPT
GPT-5 Mini
Model ID:gpt-5-mini-2025-08-07
2025-08-07Proprietary Model
ChatGPT FreeChatGPT GoChatGPT PlusChatGPT Pro|API
OverallNo.31
PopularityNo.104
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.
Knowledge Cutoff
2024-05-31
The date this AI finished learning. It may not know about things that happened after this date.
Input → Output Format
The types of content this AI can receive, and what it can produce in return.
Context Memory
400KIN128KOUT
The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.
Cost/1M Words
$0.25IN$2OUT
The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).
AI Performance Evaluation
Arena Overall Score
1390
±5As of 2026-04-02
Overall Rank
No.104
27,265 Votes
Arena by Ability
Hard Prompts
1402±6No.111
Expert Knowledge
1404±18No.101
Instruction Following
1373±8No.110
Conversation Memory
1372±9No.121
Creative
1326±10No.135
Coding
1429±9No.113
Math
1406±15No.83
Arena by Occupation
Creative Writing
1353±8No.124
Social Sciences
1396±10No.116
Media
1349±9No.109
Business
1380±9No.113
Healthcare
1401±16No.111
Legal
1392±15No.112
Software
1414±7No.116
Mathematics
1409±16No.90
Source:Arena Intelligence
Reasoning Ability
AA Intelligence Index
21%↓18%
MMLU-Pro
78%↓5%
GPQA Diamond
69%↓13%
HLE
5.0%↓12%
Math
AA Math Index
47%↓28%
AIME 2025
47%↓28%
Coding Ability
AA Coding Index
22%↓15%
LiveCodeBench
55%↓11%
SciCode
37%↓5%
TerminalBench
14%↓20%
Instruction Following
IFBench
46%↓12%
환각률 (HHEM)
13%↑2%
사실 일관성 (HHEM)
87%↓2%
Long Context
AA-LCR
36%↓28%
Agentic AI Ability
TAU2
32%↓39%
Speed
Standard Mode
90tok/sec↑12
First Output 0.82s
Artificial Analysis
Reasoning Mode
88tok/sec↑15
First Output 48.03s
Artificial Analysis