o1-mini
OpenAIOpenAI o-seriesProprietary
描述
o1-mini is a cost-efficient language model developed by OpenAI, designed for advanced reasoning tasks while minimizing computational resources.
發布日期
2024-09-12
參數規模
—
上下文長度
—
支援模態
text
能力雷達圖
28
general
58
coding
71
reasoning
43
science
67
agents
0
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
85.2%自報
SuperGLUE
75.0%自報
Math
MATH-500
90.0%自報
Reasoning
HumanEvalOpenAI (2021)
92.4%自報
GPQANYU + Cohere + Anthropic (2023)
60.0%自報
Safety
Cybersecurity CTFs
28.7%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))94.4
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))74.2
Aime(MAA (Mathematical Association of America))60.3
Gpqa(NYU + Cohere + Anthropic (2023))60.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))57.6
Intelligence Index(Artificial Analysis)9.8
Hle(Center for AI Safety + Scale AI (2025))3.6
LLM Stats 分類評分
(LLM Stats (zeroeval))Language90
Legal90
Math90
Finance90
Healthcare90
Code90
Reasoning80
General70
Physics60
Biology60
Chemistry60
Safety30
定價
輸入價格免費
輸出價格免費
混合價格(3:1)免費
速度
Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s
供應商價格排行
供應商價格排行
1 個供應商
供應商輸入輸出
1Helicone
$1.1
$4.4
比較該模型在不同 API 供應商之間的定價。