Institute of Foundation ModelsReleased Sep 3, 2026

K2 Horizon 375B A23B

Compare

Context window524.3K

Parameters375B

Provider endpoints0

Benchmark results11

Reasoning Open weights

Measured performance

Benchmark results

All leaderboards ↗

Artificial Analysis Intelligence Index ↗4.3.2

30.5

Effort not specified

Independent resultChecked Oct 18, 2026

AA-Briefcase ↗1.1

1,295.77

Effort not specified

Independent resultChecked Oct 18, 2026

GDPval-AA ↗2.1

1,360.53

Effort not specified

Independent resultChecked Oct 18, 2026

AutomationBench-AA ↗AA Index 4.3.2 collection

37.21%

Effort not specified

Independent resultChecked Oct 18, 2026

Terminal-Bench 4.0 · AA ↗4.0

1.52%

Effort not specified · Harness unreported

Independent resultChecked Oct 18, 2026

SciCode ↗AA Index 4.3.2 collection

42.94%AA · Under review

Effort not specified

Independent resultChecked Oct 18, 2026

Humanity’s Last Exam ↗AA Index 4.3.2 collection

31.97%

Effort not specified

Independent resultChecked Oct 18, 2026

GDP.pdf ↗AA Index 4.3.2 collection

7.4%

Effort not specified

Independent resultChecked Oct 18, 2026

CritPt ↗AA Index 4.3.2 collection

4.57%AA · Under review

Effort not specified

Independent resultChecked Oct 18, 2026

AA-Omniscience ↗AA Index 4.3.2 collection

-2.97

Effort not specified

Independent resultChecked Oct 18, 2026

AA-LCR ↗1.1

80%

Effort not specified

Independent resultChecked Oct 18, 2026

Access & cost

Prices across providers

0 quotes

No listed provider price

Artificial Analysis ↗

Model specifications

Developer: Institute of Foundation Models
Modality: Language
Context: 524,288 tokens
Maximum output: Not reported
Weights: Open weights
Released: Sep 3, 2026
First discovered: Oct 16, 2026

Exact identities

artificial-analysisbb3d7e75-8e22-4082-b9d6-1db0803e042f

Sources

Artificial Analysis ↗

Updated Oct 18, 2026