BlogLLM Benchmark Scores as Published, Side by Side
MultiLoKo: Results as Published
Every result the catalog holds for MultiLoKo: 3 models from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area MultilingualMaintainer Meta (Dieuwke Hupkes and co-authors)Introduced 2025Data version 2026103001, as of 2026-10-30
MultiLoKo tests multilingual knowledge with 500 locally relevant questions in each of 31 languages, plus translated versions that show how much an answer depends on the language of the question. Publishers print the average score across languages.
MultiLoKo
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 42.2% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 51.1% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 38.7% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.