K2 Horizon 375B A23B

Institute of Foundation Models

Release Date

2026-09-03

Parameters

—

Context Length

—

Modalities

—

Capability Radar

general

coding

reasoning

science

agents

multimodal

Rankings

Domain	#Rank	Score	Source
Code Ranking	71	80.0	AA
General Ranking	172	50.0	AA
Science	98	67.0	AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

No benchmark data available

AA Evaluation Indices

(Artificial Analysis)

Gpqa(NYU + Cohere + Anthropic (2023))

87.3

Lcr(Artificial Analysis)

80.0

Terminalbench V2 1

71.9

Coding Index(Artificial Analysis)

61.5

Scicode(UIUC + Argonne National Lab (2024))

42.9

Tau Banking

34.2

Hle(Center for AI Safety + Scale AI (2025))

32.0

Intelligence Index(Artificial Analysis)

30.5

Terminalbench V4 0

1.5

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

Input PriceFree

Output PriceFree

Blended Price (3:1)Free

Speed

Tokens/sec181.5

Time to First Token1.85s

Time to Answer12.87s

Provider Price Ranking

No provider data available

External Sources

Artificial Analysis