跳轉到主要內容

GPT-5 (high)

OpenAIGPTProprietary

描述

GPT-5 is a flagship model from OpenAI designed for coding, reasoning, and agentic tasks across domains. It is optimized for coding and agentic tasks with higher reasoning capabilities and medium speed.

發布日期
2025-08-07
參數規模
上下文長度
400K
支援模態
file, image, text

能力雷達圖

55
general
54
coding
95
reasoning
59
science估算
80
agents
90
multimodal

Science 在缺少專門科學評測時使用推理能力代理估算。

排行榜排名

領域#排名分數來源
智能体与工具57
55.0
LS
代码能力榜47
74.0
AA
通用能力榜34
83.0
AA
数学推理6
97.0
AA
多模态榜21
84.0
LS
推理能力41
72.0
LS
科学能力41
74.0
AA

基準測試分數 (LLM Stats)

Agents

BrowseComp54.9%自報

Biology

GPQA85.7%自報

Code

SWE-Lancer (IC-Diamond subset)100.0%自報
HumanEval93.4%自報
Aider-Polyglot88.0%自報
SWE-Bench Verified74.9%自報

Communication

Tau2 Telecom96.7%自報
Tau2 Retail81.1%自報
Multi-Challenge69.6%自報
Tau2 Airline62.6%自報

Finance

MMLU92.5%自報

General

MMMU84.2%自報
MMMU-Pro78.4%自報
Internal API instruction following (hard)64.0%自報
LongFact Objects0.8%自報
LongFact Concepts0.7%自報

Healthcare

VideoMMMU84.6%自報
HealthBench Hard1.6%自報

Language

COLLIE99.0%自報

Long Context

OpenAI-MRCR: 2 needle 128k95.2%自報
OpenAI-MRCR: 2 needle 256k86.8%自報

Math

AIME 202594.6%自報
HMMT 202593.3%自報
MATH84.7%自報
FrontierMath26.3%自報
Humanity's Last Exam24.8%自報

Multimodal

VideoMME w sub.86.7%自報
CharXiv-R81.1%自報

Reasoning

BrowseComp Long Context 128k90.0%自報
BrowseComp Long Context 256k88.8%自報
Graphwalks BFS <128k78.3%自報
Graphwalks parents <128k73.3%自報
ERQA65.7%自報
FActScore1.0%自報

AA 評測指數

Math Index
94.3
Intelligence Index
44.6
Coding Index
36.0
Math 500
1.0
Aime
1.0
Aime 25
0.9
Mmlu Pro
0.9
Gpqa
0.9
Tau2
0.8
Livecodebench
0.8
Lcr
0.8
Ifbench
0.7
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.3

LLM Stats 分類評分

Robotics
20
Spatial Reasoning
6
Multimodal
4
Vision
3
Reasoning
2
Writing
100
Language
100
Long Context
100
Video
90
Biology
90
Chemistry
90
Code
90
Finance
90
Legal
90
Physics
90
Tool Calling
80
Communication
80
General
80
Frontend Development
70
Healthcare
70
Math
70
Search
70
Structured Output
60
Agents
50

定價

輸入價格$1.25 / 1M tokens
輸出價格$10 / 1M tokens
混合價格(3:1)$3.438 / 1M tokens

速度

Tokens/秒95.3 tokens/s
首Token延遲98.86s
首回答延遲98.86s

可用提供商

(LS 內部計價單位)

暫無提供商資料

外部連結