Confirm Action

Are you sure you want to proceed?

Planned benchmark facet · ranking not published

Which models are best at factual consistency?

Avoid contradictions, invented details, and attribution drift.

This is the evaluation plan, not a model leaderboard.

No model order or score is shown. Candidate external benchmarks and planned first-party comparisons become evidence only after their exact release gates pass; retired benchmark grades are not reused.

First-party pairwise plan

Six distinct tasks for this facet

5

exploration tasks

Used for comparison coverage and calibrated refinement.

1

sealed holdout task

Kept out of model and judge tuning until release validation.

6

tasks in total

One of four equally weighted facets in this collection.

First-party, task-local pairwise comparisons with deterministic validators acting as hard gates. The final task remains sealed from model and judge tuning until release validation.

Collection-level external evidence map

Candidate benchmarks that can inform this skill

These sources are mapped to Summarization & Grounded Knowledge, then identity-partitioned and lineage-deduplicated. They are supporting inputs, not a substitute for direct task-local pairwise results, and no score is reproduced on this page.

Artificial Analysis

AA-Omniscience and AA-LCR

Mapped and runnable
Evidence role
supporting
Maximum directness
45%
Declared subject
foundation model
Usable lineages mapped
2

Capabilities: non hallucination, long context reasoning.

Mapped fields: AA-Omniscience Non-hallucination Rate, AA-LCR.

  • • source redistribution is conditional: assumed

LMArena Leaderboard Dataset

Document arena

Mapped and runnable
Evidence role
supporting
Maximum directness
35%
Declared subject
foundation model
Usable lineages mapped
1

Capabilities: document preference.

Mapped fields: LMArena Document (style controlled) — Overall.

Vectara Hallucination Leaderboard

Vectara Hallucination Leaderboard

Score feed not yet integrated
Evidence role
primary
Maximum directness
75%
Declared subject
foundation model
Usable lineages mapped
0

Capabilities: summary consistency.

  • • source is absent from the checked-in source registry

Current blockers

Why no ranking is live

  • No approved combined collection artifact has been released.
  • The parent collection has not passed its publication gate.
  • No approved facet-level result artifact has been released.

Publication gate

What must pass first

  1. 1Combine at least one eligible external result with at least one first-party pairwise result.
  2. 2Retain at least 2 independent evidence lineages and 8 eligible model configurations.
  3. 3Complete at least 3 facet tasks with at least 80% required-task coverage.
  4. 4Show that this facet is materially distinct, then pass reliability and sealed-release stability checks.

Summarization & Grounded Knowledge

Explore all four planned skills

Meeting notes Capture decisions, owners, deadlines, and unresolved items. Long-document summaries Preserve important coverage and caveats across long source material. Grounded question answering Answer only from supplied evidence and expose insufficient support. Factual consistency Avoid contradictions, invented details, and attribution drift.
Back to Summarization & Grounded Knowledge Sources and safeguards