跳轉到主要內容

Grok 3

xAIGrokProprietary

描述

Grok 3, launched by xAI on February 17, 2025, is an advanced AI model with significantly enhanced capabilities compared to Grok 2, boasting an order of magnitude increase in performance. Trained on a vast dataset that includes legal documents among others, and utilizing a massive compute infrastructure with around 200,000 GPUs in a Memphis data center, Grok 3's training used ten times more compute than its predecessor. It features specialized models like Grok 3 Reasoning and Grok 3 Mini Reasoning for complex problem-solving, and it excels in benchmarks like AIME for mathematics and GPQA for PhD-level science.

發布日期
2025-02-19
參數規模
上下文長度
131K
支援模態
image, text

能力雷達圖

39
general
29
coding
57
reasoning
45
science估算
0
agents
80
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201
41.0
AA
通用能力榜186
52.0
AA
数学推理150
60.0
AA
科学能力210
47.0
AA

基準測試分數 (LLM Stats)

Biology

GPQA84.6%自報

Code

LiveCodeBench79.4%自報

General

MMMU78.0%自報

Math

AIME 202593.3%自報
AIME 202493.3%自報

AA 評測指數

Math Index
58.0
Intelligence Index
25.2
Coding Index
19.8
Math 500
0.9
Mmlu Pro
0.8
Gpqa
0.7
Aime 25
0.6
Lcr
0.5
Tau2
0.5
Ifbench
0.5
Livecodebench
0.4
Scicode
0.4
Aime
0.3
Terminalbench Hard
0.1
Hle
0.1

LLM Stats 分類評分

Math
90
Reasoning
90
Vision
80
Biology
80
Chemistry
80
Code
80
General
80
Healthcare
80
Multimodal
80
Physics
80

定價

輸入價格$3 / 1M tokens
輸出價格$15 / 1M tokens
混合價格(3:1)$6 / 1M tokens

速度

Tokens/秒43.6 tokens/s
首Token延遲0.59s
首回答延遲0.59s

可用提供商

(LS 內部計價單位)
提供商輸入價格輸出價格
xAI3.0M15.0M

外部連結