FACTS Grounding v2 D
AI benchmark · Reasoning
What is FACTS Grounding v2?
FACTS Grounding v2 measures whether a model's long-form responses to user requests about a supplied context document (up to 32k tokens) are fully grounded in that document, scored by an updated LLM judge ensemble.
General capability mostly
“FACTS Grounding v2 is an updated version of FACTS Grounding, which tests grounding to a given document, with improved judges.”
arxiv.org/html/2512.10791v1 ↗
Paper: arxiv.org/html/2512.10791v1 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
FACTS Grounding earlier version
FACTS Grounding V1 earlier version
Tier D
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- no usage data
- in curated RL directories (1 pt)
How we got to tier D
- Adoption: no usage data. Tier D.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where FACTS Grounding v2 sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-21 snapshot.