# FACTS Search V2 (October 20 run) leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-facts-search-v2-oct20

Every model the catalog carries a published FACTS Search V2 (October 20 run) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Tool-assisted answering with an automated grader |
| Tasks | Search-assisted factual questions; public and held-out sets |
| Difficulty | — |
| Published by | [FACTS Search V2 (October 20 run) methodology](https://www.kaggle.com/code/aminmohamedmohami/facts-v2-search-on-implementation) |

FACTS Search V2 at task revision 6 as captured on October 20, 2026, before Kaggle re-ran the board at revision 7.

## FACTS Search V2 (October 20 run) ranking

No model in the catalog has a published FACTS Search V2 (October 20 run) score. The benchmark is defined by FACTS Search V2 (October 20 run) methodology, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
