AI Tools Review

K2 Horizon 375B A23B

By Institute of Foundation Models

Released: 2026-09-03

LLM
Institute of Foundation Models
Open Weights
Free

K2 Horizon 375B A23B is Institute of Foundation Models's open-weight AI model, released 03/09/2026. IFM's Hugging Face card for the flagship K2 Horizon (375B total, 23B active, Apache 2.0, 512K context) prints a chart of 18 benchmarks against four open-weight models (Nemotron 3 Ultra, Inkling xhigh, MiniMax-M3, GLM 5.2 max) and three closed ones (GPT 5.6 Luna, GPT 5.6 Terra, Claude Sonnet 5). It tops only SWE-Atlas-QnA and trails the best closed model on most rows. The card states no release date; 3 September 2026 comes from MBZUAI's launch announcement as cited in our article. Recommended settings are reasoning_effort high, temperature 1.0, top_p 0.95.

Visit K2 Horizon 375B A23B

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

How does K2 Horizon 375B-A23B score on independent benchmarks?

K2 Horizon 375B-A23B ranks #26 of 28 models on the Artificial Analysis Intelligence Index (v5.0.1) with a score of 17.8, as measured on 22 November 2026.

Intelligence Index
17.8
AA v5.0.1
Coding Agent Index
n/a
Cost per task
n/a
AA Intelligence Index task
Price per 1M tokens
n/a / n/a
input / output

Where does K2 Horizon 375B-A23B rank against other models?

How does K2 Horizon 375B-A23B do on individual tests?

Evaluation (run by Artificial Analysis)K2 Horizon 375B-A23BBest of any model
Terminal-Bench 4.01.5%67.2%
FrontierCode 2.011.8%48.8%
Humanity's Last Exam32%74.3%
GDPval-AA (Elo)13631866

How has K2 Horizon 375B-A23B's score changed over time?

We have tracked K2 Horizon 375B-A23B on Intelligence Index v5.0.1 since 22/11/2026. A point is added each day the score, coding index or price changes, so this chart fills in over time.

What does the K2 Horizon 375B-A23B system card report?

IFM's Hugging Face card for the flagship K2 Horizon (375B total, 23B active, Apache 2.0, 512K context) prints a chart of 18 benchmarks against four open-weight models (Nemotron 3 Ultra, Inkling xhigh, MiniMax-M3, GLM 5.2 max) and three closed ones (GPT 5.6 Luna, GPT 5.6 Terra, Claude Sonnet 5). It tops only SWE-Atlas-QnA and trails the best closed model on most rows. The card states no release date; 3 September 2026 comes from MBZUAI's launch announcement as cited in our article. Recommended settings are reasoning_effort high, temperature 1.0, top_p 0.95.

These are IFM (Institute of Foundation Models, MBZUAI)'s own published results (self-reported, with the vendor's harness and settings), so they are not directly comparable with other labs' numbers. Source: IFM/K2-Horizon-375B-A23B on Hugging Face. Last checked 22/11/2026.

Agents & tool use

BenchmarkK2 Horizon 375B-A23BNemotron 3 UltraInkling (xhigh)MiniMax-M3
GDPval-AA1441 Elo116212341380
tau3-Banking34%14.2%29.1%15.3%
Toolathlon Verified65.3%34.3%45.5%53.7%
Automation Bench Public25.3%8%12.8%20.5%
Apex-Agents (pass@1)Subset of text-only tasks24.8%9%19%23.8%
MCPMark67.7%45.7%51.2%48.8%
BrowseCompDiscard-all@95k context setting; other models may use different harnesses72.8%44.4%77.1%83.5%
WildClawBenchSubset of text-only tasks50.9%34.2%52.3%56.4%

Coding

BenchmarkK2 Horizon 375B-A23BNemotron 3 UltraInkling (xhigh)MiniMax-M3
Terminal-Bench 2.1Figure printed on the card chart; IFM later reported 66.9% after a reward-hacking audit (reported in our article, not on the card)70.2%53.9%55.1%65.2%
SciCode42.7%39.9%46.1%45.4%
SWE-Atlas-QnA (strict)Strict mode, no internet access48.4%n/a25.5%42.3%
SWE Bench Pro (strict)Strict mode, no internet access42.6%38.7%43.1%43.8%

Knowledge & science

BenchmarkK2 Horizon 375B-A23BNemotron 3 UltraInkling (xhigh)MiniMax-M3
Humanity's Last Exam (no tools)32%28.4%31.9%39%
GPQA Diamond87.3%86.7%87.2%92.9%
CritPt8.6%3.1%5.4%3.7%
AA-Omniscience Accuracy23%23%42%17%

Long context

BenchmarkK2 Horizon 375B-A23BNemotron 3 UltraInkling (xhigh)MiniMax-M3
AA-LCR76%71%73.3%80.3%

Safety & honesty

BenchmarkK2 Horizon 375B-A23BNemotron 3 UltraInkling (xhigh)MiniMax-M3
AA-Omniscience Non-Hallucination74.7%70%32%82%

What did safety testing find for K2 Horizon 375B-A23B?

Safety level: Not published on the model card

    Independent figures: Artificial Analysis, refreshed daily on our AI model benchmarks page. Full analysis: our K2 Horizon 375B-A23B deep dive.

    Institute of Foundation Models Model Timeline

    K2 Horizon 375B A23BCurrent

    512K tokens (524,288) context

    Specifications

    context Window512K tokens (524,288)