models · k-intelligence
Mi:dm K 2.5 Pro — catalogued from third-party evaluation data; no weights held by Sovereign Frontier.
| Method | third-party-report |
|---|
| Publisher | k-intelligence |
|---|---|
| Origin | South Korea |
| Licence | MIT |
| MMLU-Pro | 80.9 |
|---|---|
| GPQA Diamond | 70.1 |
| AIME 2025 | 76.7 |
| LiveCodeBench | 65.6 |
| IFBench | 49.3 |
| Humanity's Last Exam | 8.1 |
Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.
Registry record as of 2026-08-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.