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.
发布日期
2025-02-19
参数规模
—
上下文长度
131K
支持模态
image, text
能力雷达图
39
general
29
coding
57
reasoning
45
science估算
0
agents
80
multimodal
Science 在缺少专门科学评测时使用推理能力代理估算。
排行榜排名
基准测试分数 (LLM Stats)
Biology
GPQA
84.6%自报
Code
LiveCodeBench
79.4%自报
General
MMMU
78.0%自报
Math
AIME 2025
93.3%自报
AIME 2024
93.3%自报
AA 评测指数
Math Index58.0
Intelligence Index25.2
Coding Index19.8
Math 5000.9
Mmlu Pro0.8
Gpqa0.7
Aime 250.6
Lcr0.5
Tau20.5
Ifbench0.5
Livecodebench0.4
Scicode0.4
Aime0.3
Terminalbench Hard0.1
Hle0.1
LLM Stats 分类评分
Math90
Reasoning90
Vision80
Biology80
Chemistry80
Code80
General80
Healthcare80
Multimodal80
Physics80
定价
输入价格$3 / 1M tokens
输出价格$15 / 1M tokens
混合价格(3:1)$6 / 1M tokens
速度
Tokens/秒43.6 tokens/s
首Token延迟0.59s
首回答延迟0.59s
可用提供商
(LS 内部计价单位)| 提供商 | 输入价格 | 输出价格 |
|---|---|---|
| xAI | 3.0M | 15.0M |