GPT-4.1
OpenAIGPTProprietary
描述
GPT-4.1 is OpenAI's latest and most advanced flagship model, significantly improving upon GPT-4 Turbo in performance across benchmarks, speed, and cost-effectiveness.
發布日期
2025-04-14
參數規模
—
上下文長度
1.0M
支援模態
file, image, text
能力雷達圖
39
general
32
coding
49
reasoning
44
science估算
60
agents
85
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
基準測試分數 (LLM Stats)
Biology
GPQA
66.3%自報
Code
SWE-Bench Verified
54.6%自報
Aider-Polyglot Edit
52.9%自報
Aider-Polyglot
51.6%自報
Communication
Multi-IF
70.8%自報
TAU-bench Retail
68.0%自報
TAU-bench Airline
49.4%自報
Multi-Challenge
38.3%自報
Finance
MMLU
90.2%自報
General
IFEval
87.4%自報
MMMLU
87.3%自報
MMMU
74.8%自報
Internal API instruction following (hard)
49.1%自報
Language
COLLIE
65.8%自報
Long Context
ComplexFuncBench
65.5%自報
OpenAI-MRCR: 2 needle 128k
57.2%自報
OpenAI-MRCR: 2 needle 1M
46.3%自報
Graphwalks parents >128k
25.0%自報
Graphwalks BFS >128k
19.0%自報
Math
MathVista
72.2%自報
AIME 2024
48.1%自報
AIME 2025
46.4%自報
HMMT 2025
28.9%自報
Humanity's Last Exam
5.4%自報
Multimodal
CharXiv-D
87.9%自報
Video-MME (long, no subtitles)
72.0%自報
CharXiv-R
56.7%自報
Reasoning
Graphwalks BFS <128k
61.7%自報
Graphwalks parents <128k
58.0%自報
AA 評測指數
Math Index34.7
Intelligence Index26.3
Coding Index21.8
Math 5000.9
Mmlu Pro0.8
Gpqa0.7
Lcr0.6
Tau20.5
Livecodebench0.5
Aime0.4
Ifbench0.4
Scicode0.4
Aime 250.3
Terminalbench Hard0.1
Hle0.0
LLM Stats 分類評分
Finance90
Legal90
Healthcare80
Instruction Following80
Language80
Structured Output70
Writing70
Biology70
Chemistry70
General70
Multimodal70
Physics70
Tool Calling60
Vision60
Communication60
Reasoning60
Code50
Frontend Development50
Math50
Spatial Reasoning40
Long Context40
定價
輸入價格$2 / 1M tokens
輸出價格$8 / 1M tokens
混合價格(3:1)$3.5 / 1M tokens
速度
Tokens/秒108.1 tokens/s
首Token延遲0.55s
首回答延遲0.55s
可用提供商
(LS 內部計價單位)| 提供商 | 輸入價格 | 輸出價格 |
|---|---|---|
| OpenAI | 2.0M | 8.0M |