ChatGPT
ChatGPT

GPT-5

Model ID:gpt-5-2025-08-07
2025-08-07Proprietary Model
API
OverallNo.30
PopularityNo.45

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

Knowledge Cutoff
2024-09-30

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
$1.25IN$10OUT

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
1434
±5
As of 2026-04-02
Overall Rank
No.45
32,245 Votes
Arena by Ability
Hard Prompts
1446±6No.52
Expert Knowledge
1459±16No.39
Instruction Following
1409±7No.63
Conversation Memory
1420±9No.64
Creative
1375±10No.86
Coding
1468±8No.57
Math
1433±14No.39
Arena by Occupation
Creative Writing
1397±8No.67
Social Sciences
1444±9No.54
Media
1397±8No.51
Business
1414±9No.65
Healthcare
1456±15No.47
Legal
1454±14No.36
Software
1453±7No.69
Mathematics
1442±14No.41
Reasoning Ability
AA Intelligence Index
22%↓17%
MMLU-Pro
82%↓1%
GPQA Diamond
69%↓13%
HLE
5.8%↓11%
Math
AA Math Index
48%↓26%
AIME 2025
48%↓26%
Coding Ability
AA Coding Index
21%↓15%
LiveCodeBench
54%↓11%
SciCode
38%↓4%
TerminalBench
13%↓21%
Instruction Following
IFBench
45%↓12%
환각률 (HHEM)
15%↑4%
사실 일관성 (HHEM)
85%↓4%
Long Context
AA-LCR
64%↑0%
Agentic AI Ability
TAU2
0.0%↓71%
Speed
Standard Mode
77tok/sec↓1
First Output 1.03s
Artificial Analysis
Reasoning Mode
85tok/sec↑13
First Output 41.72s
Artificial Analysis