benchgap
Other · model

K2 Horizon 375B A23B benchmark scores

As of 2026-10-07, K2 Horizon 375B A23B (Other) has measured scores on 9 benchmarks and estimated scores on 5 more.

BenchmarkScoreSource
Terminal-Bench 2.171.9%measured
Terminal-Bench 4.01.5%measured
Terminal-Bench Science 0.12.6%estimated ± 6.5 pp, medium confidence
GPQA Diamond87.3%measured
SciCode42.9%measured
CritPt4.6%measured
GDP.pdf7.4%measured
τ³-Bench Banking34.2%measured
MMMU-Pro75.1%estimated ± 2.6 pp, medium confidence
AA-AnalystAgent19.1%estimated ± 7.8 pp, medium confidence
Harvey LAB94.2%estimated ± 2.1 pp, medium confidence
Humanity's Last Exam32.0%measured
AutomationBench37.2%measured
EnterpriseOps-Gym39.5%estimated ± 5.3 pp, medium confidence