cross-encoder/ms-marco-minilm-l-12-v2 — Withdrawn — shutdown 8 August 2026

For cross-encoder/ms-marco-minilm-l-12-v2, provider is IBM watsonx.ai; lifecycle status is Withdrawn; deprecation announced is 8 May 2026; shutdown / retirement date is 8 August 2026; recommended replacement is granite-embedding-278m-multilingual, multilingual-e5-large; platform / deployment scope is watsonx.ai embedding models (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers), recorded from its source on 2026-09-16.

Values marked our reading are our classification of what the source says — the source does not print them in those words. The quote below is the evidence for each one; judge it yourself.

What the source says

ms-marco-minilm-l-12-v2 (Dallas, Frankfurt, London, Tokyo, Sydney, Toronto, AWS Mumbai, AWS GovCloud data centers) cross-encoder/ms-marco-minilm-l-12-v2 | 21 October 2024 | 8 May 2026 | 8 August 2026 | granite-embedding-278m-multilingual, multilingual-e5-large |

— ibm.com, retrieved 2026-09-16

Where each value comes from

The value above is stated away from the sentence quoted with the answer, so the passage that states it is shown here too.

— all from ibm.com, retrieved 2026-09-16

Source

• ibm.comhttps://www.ibm.com/docs/en/watsonx/saas?topic=models-foundation-model-lifecycle

Last verified against source: 2026-09-16. Due for re-check by 2026-10-16. This page as Markdown · OKF bundle · full dataset as JSON.