Atlas

Models

← All models

K2 Horizon 375B A23B

LLM360

The Institute of Foundation Models' flagship K2 Horizon sparse checkpoint, published through the K2/LLM360 program. It has native 524,288-token context and request-level reasoning effort controls.

Benchmark scores

BenchmarkScore
AA-Briefcase Elo1298
AA-Briefcase v1.1 Elo1303
AA-LCR v1.180.0
AA-Omniscience Index-3.0
Artificial Analysis Intelligence Index v4.330.8
Artificial Analysis Intelligence Index v4.3.230.5
Artificial Analysis Omniscience Accuracy18.2
Artificial Analysis Omniscience Hallucination Rate25.9
AutomationBench-AA 1.0.637.2
Capability153.6
CritPt (avg@5)4.6
GDP.pdf (Artificial Analysis, All-pass)7.4
GDP.pdf (Artificial Analysis, Mean Criteria)54.0
GDPval-AA v21400
GDPval-AA v2.11349
GPQA Diamond (Artificial Analysis avg@5)87.3
Humanity's Last Exam (Text-Only)32.0
SciCode 1.0.1 (Artificial Analysis)42.9
Terminal-Bench 2.171.9
Terminal-Bench 4.0 (Artificial Analysis)1.5
𝜏³-Banking34.2
Loading Atlas data…