Model profile
K2 V2
2025-12-03release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #125 of 311); its weakest is AA-Omniscience (hallucination_rate, #125 of 311).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗k2-v2
- Hugging Face ↗LLM360/K2-V2-Instruct
- Official model page ↗Configuration-level model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #125 / 311 | 0.7644 | ↓ lower | Source ↗official |