跳轉到主要內容

o1

OpenAIOpenAI o-seriesProprietary

描述

A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced capabilities in formal reasoning while maintaining strong general capabilities.

發布日期
2024-12-05
參數規模
上下文長度
200K
支援模態
file, image, text

能力雷達圖

43
general
39
coding
80
reasoning
48
science估算
60
agents
70
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
代码能力榜157
49.0
AA
通用能力榜104
66.0
AA
数学推理55
87.0
AA
科学能力169
51.0
AA

基準測試分數 (LLM Stats)

Biology

GPQA78.0%自報
GPQA Biology69.2%自報

Chemistry

GPQA Chemistry64.7%自報

Code

HumanEval88.1%自報
SWE-Bench Verified41.0%自報

Communication

TAU-bench Retail70.8%自報
TAU-bench Airline50.0%自報

Factuality

SimpleQA47.0%自報

Finance

MMLU91.8%自報

General

MMMLU87.7%自報
MMMU77.6%自報
LiveBench67.0%自報

Math

GSM8k97.1%自報
MATH96.4%自報
MGSM89.3%自報
AIME 202474.3%自報
MathVista71.8%自報
FrontierMath5.5%自報

Physics

GPQA Physics92.8%自報

AA 評測指數

Intelligence Index
30.8
Coding Index
20.5
Math 500
1.0
Mmlu Pro
0.8
Gpqa
0.7
Aime
0.7
Ifbench
0.7
Livecodebench
0.7
Tau2
0.6
Lcr
0.6
Scicode
0.4
Terminalbench Hard
0.1
Hle
0.1

LLM Stats 分類評分

Finance
90
Language
90
Legal
90
Biology
80
Chemistry
80
Healthcare
80
Math
80
Physics
80
Vision
70
General
70
Multimodal
70
Reasoning
70
Tool Calling
60
Code
60
Communication
60
Factuality
50
Frontend Development
40

定價

輸入價格$15 / 1M tokens
輸出價格$60 / 1M tokens
混合價格(3:1)$26.25 / 1M tokens

速度

Tokens/秒111.0 tokens/s
首Token延遲22.15s
首回答延遲22.15s

可用提供商

(LS 內部計價單位)

暫無提供商資料

外部連結