K2 Horizon 375B A23B, a new open weights model from UAE's MBZUAI, scores 47 on the Artificial Analysis Intelligence Index, with relatively strong agentic performance and a 30 point jump over its predecessor
K2 Horizon 375B A23B is an open weights Mixture-of-Experts model with 375B total and 23B active parameters from @IFM_MBZUAI, MBZUAI's Institute of Foundation Models. It scores 47 on the Intelligence Index, alongside models such as MiniMax-M3 (45, also a MoE with 23B active parameters), and a large upgrade from its predecessor K2 Think V2 (17, 70B dense model). It leads nearby open weights models on agentic evals and has a low hallucination rate, but trails on knowledge and the hardest reasoning evals. K2 Think V2 ranks among the most open models on our Openness Index; MBZUAI is updating the supporting documentation and code for K2 Horizon and we expect to add it to the Openness Index soon.
Key takeaways:
➤ Strong on agentic tasks, weaker on knowledge and deep reasoning. MiniMax-M3, a recent model that is close to it on the Intelligence Index, makes the cleanest comparison: K2 Horizon 375B A23B leads on GDPval-AA, our real-world knowledge work benchmark (Elo 1430 vs 1380), and on 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%)
➤ Low hallucination rate, driven by abstention rather than knowledge. K2 Horizon 375B A23B attempts only 40% of AA-Omniscience questions, declining the remaining 60% rather than guessing. The result is a 26% hallucination rate, among the lower rates we have measured, while accuracy is 18%, essentially unchanged from K2 Think V2
➤ A new architecture over its predecessor. K2 Horizon 375B A23B is a 375B parameter Mixture-of-Experts model with 23B active, succeeding the 70B dense K2 Think V2, and extends context from 262K to 512K tokens. Its 23B active parameters match MiniMax-M3 (428B total, 23B active)
Key model details:
➤ Architecture: Mixture-of-Experts, 375B total parameters, 23B active
➤ Context window: 512K tokens
➤ Multimodality: Text input and output only
➤ Pricing and availability: Yet to be announced
➤ Licensing: Open weights (license details to be announced)
K2 Horizon 375B A23B performs strongly on agentic work for its intelligence level: its GDPval-AA Elo of 1430 leads other models at a similar intelligence level, such as MiniMax-M3 (1380), on real-world knowledge work tasks such as preparing presentations and analysis
K2 Horizon 375B A23B would rather decline a question than guess. It attempts just 40% of AA-Omniscience questions, producing a 26% hallucination rate that ranks among the lower rates we have measured, with accuracy of 18% essentially unchanged from its predecessor. The reduced hallucination is a huge improvement over K2 Think V2 (71%), taking the AA-Omniscience Index score from -40 to -3
Full breakdown of the individual evaluations in the Artificial Analysis Intelligence Index for K2 Horizon 375B A23B:
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
An open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition →mixture-of-expertsA model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.Full definition → that leads nearby peers on agentic and real-world knowledge-work evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → while trailing on hard reasoning, so it is worth routing tool-use workloads to and keeping off deep reasoning tasks.
Read the full thread on X ↗
