Model profile
mbzuai ifmdeveloper
2026-09-01release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. K2 Horizon 375B A23B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #22 of 345); its weakest is AA-Omniscience (hallucination_rate, #22 of 345).
Freedom. K2 Horizon 375B A23B does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗bb3d7e75-8e22-4082-b9d6-1db0803e042f
- Hugging Face ↗IFM/K2-Horizon-375B-A23B
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #22 / 345 | ↓0.2585 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.