GPT-4.5 (Preview)
OpenAIGPTProprietary
描述
GPT-4.5 is OpenAI's most advanced model, offering improved reasoning, coding, and creative capabilities with faster performance and longer context handling than GPT-4. It features enhanced instruction following, reduced hallucinations, and better factual accuracy.
发布日期
2025-02-27
参数规模
—
上下文长度
—
支持模态
image, text
能力雷达图
10
general
50
coding
80
reasoning
60
science估算
60
agents
70
multimodal
缺少专门科学评测时，Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Chat
IFEvalGoogle Research (2023)
88.2%自报
Multi-IF
70.8%自报
TAU-bench Retail
68.4%自报
Multi-Challenge
43.8%自报
Factuality
SimpleQA
62.5%自报
General
MMLU
90.8%自报
Internal API instruction following (hard)
54.0%自报
Aider-Polyglot Edit
44.9%自报
Language
MMMLU
85.1%自报
COLLIE
72.3%自报
Long Context
ComplexFuncBench
63.0%自报
OpenAI-MRCR: 2 needle 128k
38.5%自报
Math
GSM8k
97.0%自报
MathVista
72.3%自报
AIME 2024
36.7%自报
Multimodal
MMMU
75.2%自报
Reasoning
CharXiv-D
90.0%自报
HumanEvalOpenAI (2021)
88.0%自报
Graphwalks parents <128k
72.6%自报
Graphwalks BFS <128k
72.3%自报
GPQANYU + Cohere + Anthropic (2023)
69.5%自报
CharXiv-R
55.4%自报
TAU-bench Airline
50.0%自报
SWE-Bench Verified
38.0%自报
SWE-Lancer
37.3%自报
SWE-Lancer (IC-Diamond subset)
17.4%自报
AA 评测指数
(Artificial Analysis)Intelligence Index(Artificial Analysis)9.6
LLM Stats 分类评分
(LLM Stats (zeroeval))Legal90
Finance90
Instruction Following80
Language80
Math80
Healthcare80
Chat70
Multimodal70
Physics70
Spatial Reasoning70
Structured Output70
Biology70
Chemistry70
Vision70
Writing70
Reasoning60
Factuality60
General60
Communication60
Tool Calling60
Long Context50
Code50
Frontend Development40
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
暂无提供商数据