MBZUAI's open K2 Horizon 375B MoE scores 47 on AA Intelligence Index, up 30 points
HongyiWang10 · x · 2026-09-04
MBZUAI's Institute of Foundation Models released K2 Horizon 375B A23B, an open-weights Mixture-of-Experts model (375B total / 23B active params). Per Artificial Analysis:
- Scores 47 on the Intelligence Index, alongside MiniMax-M3 (45, also a 23B-active MoE)
- A 30-point jump over predecessor K2 Think V2 (17, a 70B dense model)
- Leads nearby open-weights models on agentic evals, with a low hallucination rate
- Trails on knowledge and the hardest reasoning tasks
Touted as the new horizon for open source models.
Related event: MBZUAI's IFM Releases K2 Horizon: Six Fully Open Models from 0.9B to 375B(30 posts)→
More from Models
- Users want open-format export from Claude Docs as charts only save as images — BlackHC · 2026-10-20
- EMNLP study: LLM safety interventions drop up to 4.5x when distress is wrapped in delusion — MaartenSap · 2026-10-20
- Cybersecurity-focused VLM OrcaCyber-Nano-1.0 trends on Hugging Face — orcarouter · 2026-10-20
- 0.8B local model with 2,000 labels beats Jev's frontier API on banking data — kalyan_kpl · 2026-10-20
- New TTS benchmark tests 26 models across 30,564 requests: fastest at 46ms — mattturck · 2026-10-20
- Agents handle unreleased language Jai flawlessly, even compile-time execution — lucasmeijer · 2026-10-20