所有发布••

Open weights model

•

Released 2026年9月

K2 Horizon 375B A23B:智能、性能与价格分析

模型摘要

智能

18
Artificial Analysis Intelligence Index
智能为 4 档中的第 2 档。

性能

首个答案 Token 延迟 19.10秒输出速度 224 tok/s
4.7
每个 Intelligence Index 任务耗时(分钟)
性能为 4 档中的第 1 档。

成本

输入 $0.00输出 $0.00
$0.00
Intelligence Index 每项任务的成本
成本为 4 档中的第 1 档。

冗长度

输入 Token 4.74B输出/输入 1.987%
94.3M
Intelligence Index 输出 token 数
冗长度为 4 档中的第 2 档。

K2 Horizon 375B A23B 的智能水平低于平均水平,但价格很有竞争力;比较对象为其他规模相近的开放权重模型。 此外,其每任务耗时明显较短,回答也较为简洁。 该模型支持文本输入,可输出文本,上下文窗口为 524k 个 token。

K2 Horizon 375B A23B 在 Artificial Analysis Intelligence Index 上的得分为 18,在同类模型中低于平均水平(中位数:23)。在 Intelligence Index 评测中,它生成了 94.3M 个 token;与 106M 的中位数相比,其回答较为简洁。

K2 Horizon 375B A23B 每 100 万输入 token 的价格为 $0.00(很有竞争力,中位数:$0.43),每 100 万输出 token 的价格为 $0.00(很有竞争力,中位数:$1.84)。在 Intelligence Index 上评测 K2 Horizon 375B A23B 的平均每项任务成本为 $0.00。

K2 Horizon 375B A23B 完成一项 Intelligence Index 任务需 4.7 分钟,与同类模型 13.8 分钟的中位数相比明显较短(越低越好)。

Artificial Analysis Intelligence Index · Higher is better
No publicly available API
Inference time (minutes) per Intelligence Index task · Lower is better
No publicly available API
Weighted average cost (USD) per Intelligence Index task · Lower is better
No publicly available API

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index:开放权重与专有模型

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Intelligence Index 与每项任务的成本

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

能力指数

衡量模型在特定能力与行业中的表现
Finance & Accounting Index

Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100
查看更多

Agentic knowledge work, Elo

Agentic SaaS workflows

Agentic scientific research workflows in a terminal

Agentic software engineering in open-source repositories

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Physics reasoning

Agentic real-world work tasks, Elo

Medical long context reasoning

Rich, varied, well-crafted language

Well-structured, scannable, answer-first

Truthful, acknowledges uncertainty, non-sycophantic

Use of filler and generic language

AA-PersonalityBench

性格指数

每个轴对应 8 个性格指数之一:其特质 Elo z 分数的平均值,在基准测试中所有已评估模型之间换算为 1 到 100 的百分位排名

Openness Index

Artificial Analysis Openness Index:得分

Openness Index 以 0 至 100 的标准化评分衡量模型的开放程度(分数越高,越开放)

成本

每项 Intelligence Index 任务的成本

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

运行 Artificial Analysis Intelligence Index 的成本

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

价格:缓存命中、输入和输出

Price (USD per M Tokens)

性能

按每任务耗时(分钟)、输出速度(每秒 token 数)、首个答案 Token 延迟和首 Token 延迟(秒)衡量

Intelligence Index 每项任务耗时

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

输出速度

Output tokens divided by total request time, including time to first token · Higher is better

首个答案 Token 延迟

收到首个答案 token 的秒数 · 包含推理模型的“思考”时间

Token 使用量

Intelligence Index 每项任务的输出 Token 数

运行 Artificial Analysis Intelligence Index 单项任务所用输出 token 数的加权平均值

上下文窗口

上下文窗口

Context window: tokens limit · Higher is better

模型规模(仅开放权重模型)

模型规模:总参数量与活跃参数量

Comparison between total model parameters and parameters active during inference (billions)

更多详情

权重
K2 Horizon 375B A23B
Institute of Foundation Models 标志Institute of Foundation Models
18
375B
推理时启用 23B 个参数
524k
$0.00
4.7
224
Institute of Foundation Models

常见问题

关于 K2 Horizon 375B A23B 的常见问题