跳转到主要内容

Grok 4.6 (high)

SpaceXAIGrokProprietary

描述

Grok 4.6 is SpaceXAI's frontier model built for coding, agentic tasks, and knowledge work. It builds on Grok 4.5 with a particular focus on long-running agents and more ambitious interactive and visual work. The model supports text and image inputs, reasoning, function calling, structured outputs, and a 500K-token context window.

发布日期
2026-08-12
参数规模
上下文长度
500K
支持模态
image, pdf, text

能力雷达图

57
general
73
coding
95
reasoning
70
science
100
agents
80
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜11
65.0
LS
代码能力榜14
95.0
AA
通用能力榜4
96.0
AA
数学推理11
93.0
LB
推理能力4
91.0
LB
科学能力19
89.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

GDPval-AA1753.00 / 3000自报
AA-Briefcase1577.00 / 3000自报
CursorBench v3.269.9%自报
DeepSWE 1.165.9%自报
FrontierCode61.3%自报
APEX-Agents57.5%自报
APEX-SWE56.4%自报
Terminal-Bench 3.026.0%自报
Harvey LAB (Vals)15.8%自报

General

AA-Index61.0%自报

AA 评测指数

(Artificial Analysis)
Coding Index(Artificial Analysis)
76.8
Intelligence Index(Artificial Analysis)
60.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Terminalbench V2 1
0.9
Lcr(Artificial Analysis)
0.8
Scicode(UIUC + Argonne National Lab (2024))
0.5
Tau Banking
0.5
Hle(Center for AI Safety + Scale AI (2025))
0.4

LLM Stats 分类评分

(LLM Stats (zeroeval))
Legal
100
Finance
100
Productivity
100
Reasoning
100
Agents
100
General
100
Code
60

定价

输入价格$2 / 1M tokens
输出价格$6 / 1M tokens
混合价格(3:1)$3 / 1M tokens
缓存读取价格$0.5 / 1M tokens

速度

Tokens/秒62.8
首Token延迟40.45s
首回答延迟40.45s

供应商价格排行

供应商价格排行

9 个供应商

最便宜: xAI最贵: Venice AI
供应商输入输出
1xAI最便宜
$0
$0.00001
2SpaceXAI主要
$2
$6
3NanoGPT
$2
$6
4OpenRouter
$2
$6
5Kilo Gateway
$2
$6
6OpenCode Zen
$2
$6
7LLM Gateway
$2
$6
8CrossModel
$2
$6
9Venice AI
$2.27
$6.8

比较该模型在不同 API 供应商之间的定价。

外部链接