MBZUAI's open-weights K2 Horizon 375B jumps 30 points to 47 on the Intelligence Index
ArtificialAnlys · x · 2026-09-03
UAE's MBZUAI Institute of Foundation Models released K2 Horizon 375B A23B, an open-weights MoE model (375B total / 23B active) scoring 47 on the Artificial Analysis Intelligence Index — a 30-point jump over its predecessor K2 Think V2 (17) and on par with MiniMax-M3 (45).
- Architecture: 375B/23B-active MoE, context extended from 262K to 512K tokens, text-only; pricing and license details TBD.
- Strong agentic, weaker deep reasoning: leads GDPval-AA (Elo 1430 vs MiniMax-M3's 1380) and τ³-Banking (34.2% vs 15.3%), but trails on GPQA Diamond (87.3% vs 92.9%) and Humanity's Last Exam (32.0% vs 39.0%).
- Very low hallucination: it attempts only 40% of AA-Omniscience questions, declining the rest — 26% hallucination rate (predecessor: 71%) with accuracy essentially unchanged at 18%.
- K2 Think V2 ranked among the most open models; K2 Horizon is expected to join the Openness Index once docs ship.
Related event: MBZUAI's IFM Open-Sources K2 Horizon Family from 0.9B to 375B(6 posts)→
More from Models
- OpenEvidence Launches Medical AI Model Family, Darwin Scores First-Ever 100% on MedQA — benxneo · 2026-09-03
- New data: open-weight models are already in production worldwide, and cost isn't the top reason — perilli · 2026-09-03
- "Why are all the major providers down?" — multi-provider AI outage confuses users — basedjensen · 2026-09-03
- ChatGPT down today amid apparent multi-provider AI outage — Abhishekcur · 2026-09-03
- Local model users get the last laugh as major cloud AI providers go down — zeeg · 2026-09-03
- Open Athena Starts Training Marin: 535B-Parameter MoE on 18T Tokens, Fully Open — TheTuringPost · 2026-09-03