MBZUAI Institute of Foundation Models logo
MBZUAI Institute of Foundation Models
•

Open weights model

•

Released September 2026

K2 Horizon 375B A23B Intelligence, Performance & Price Analysis

API Provider Benchmarks

Model summary

Intelligence

47
Artificial Analysis Intelligence Index
4 out of 4 units for Intelligence.

Speed

N/A
Output tokens per second
Unknown out of 4 units for Speed.

Cost

In $0.00Out $0.00
N/A
Cost per Intelligence Index task
Unknown out of 4 units for Cost.

Verbosity

89M
Output tokens from Intelligence Index
2 out of 4 units for Verbosity.

K2 Horizon 375B A23B is amongst the leading models in intelligence and well priced when comparing to other open weight models of similar size. The model supports text input, outputs text, and has a 524k tokens context window.

K2 Horizon 375B A23B scores 47 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 29). When evaluating the Intelligence Index, it generated 89M tokens, which is fairly concise in comparison to the median of 110M.

Pricing for K2 Horizon 375B A23B is $0.00 per 1M input tokens (competitively priced, median: $0.30) and $0.00 per 1M output tokens (competitively priced, median: $1.17).

ReasoningYes

This page shows the reasoning version of this model.

A non-reasoning variant may also exist.

Input modality

Supports: text

Output modality

Supports: text

Context window524k
~786 A4 pages of size 12 Arial font
Total parameters375B
Active parameters23B
Number of parameters active per token during inference
LicenseApache 2.0
Model weightsHugging Face

Metrics are compared against models of the same class:

  • Non-reasoning models → compared only with other non-reasoning models
  • Reasoning models → compared across both reasoning and non-reasoning
  • Open weights models → compared only with other open weights models of the same size class:
    • Tiny: ≤4B parameters
    • Small: 4B–40B parameters
    • Medium: 40B–150B parameters
    • Large: >150B parameters
  • Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
    • <$0.15 per 1M tokens
    • $0.15–$1 per 1M tokens
    • >$1 per 1M tokens

Highlights

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Intelligence Index Comparisons

Intelligence Index vs. Cost per Intelligence Index Task

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

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Token Use

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost to Run Artificial Analysis Intelligence Index

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

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Context Window

Context Window

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Frequently Asked Questions

Common questions about K2 Horizon 375B A23B

K2 Horizon 375B A23B was released on September 3, 2026.

K2 Horizon 375B A23B was created by MBZUAI Institute of Foundation Models.

K2 Horizon 375B A23B scores 47 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 29).

When evaluated on the Intelligence Index, K2 Horizon 375B A23B generated 89M output tokens, which is better than average compared to other open weight models of similar size (median: 110M).

Yes, K2 Horizon 375B A23B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

K2 Horizon 375B A23B supports text input.

K2 Horizon 375B A23B supports text output.

No, K2 Horizon 375B A23B does not support image input. It can only process text.

No, K2 Horizon 375B A23B is not multimodal. It only supports text input.

K2 Horizon 375B A23B has a context window of 520k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, K2 Horizon 375B A23B is open weights. The model weights are publicly available and can be downloaded for self-hosting.

K2 Horizon 375B A23B has 375 billion parameters (23 billion active).

K2 Horizon 375B A23B is a Mixture of Experts (MoE) model with 375 billion total parameters, but only 23 billion active parameters are used during inference.

K2 Horizon 375B A23B is released under the Apache 2.0 license. This license allows commercial use. View license

K2 Horizon 375B A23B achieves a score of 47 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

K2 Horizon 375B A23B is an open weights model that can be self-hosted. View providers

K2 Horizon 375B A23B is an open weights model that can be downloaded and self-hosted. Compare providers