BlogLLM Benchmark Scores as Published, Side by Side
FACTS Parametric: Results as Published
Every result the catalog holds for FACTS Parametric: 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 General Knowledge and ReasoningMaintainer Google DeepMind and KaggleIntroduced 2025Data version 2026103001, as of 2026-10-30
FACTS Parametric is the closed-book part of the FACTS Benchmark Suite: trivia-style factual questions that a model must answer from its own knowledge, without search or other tools. It has public and private question sets of 1,052 items each, and the score is accuracy.
FACTS Parametric
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSeek-V4-Flash-BaseDeepSeek, released 2026-04-24 | 33.9% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V4-Pro-BaseDeepSeek, released 2026-04-24 | 62.6% | DeepSeek, DeepSeek-V4-Pro (preview) model cardchecked 2026-10-15 | - |
| DeepSeek-V3.2-BaseDeepSeek, released 2025-12-01 | 27.1% | 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.