FACTS Grounding
A benchmark evaluating language models' ability to generate factually accurate and well-grounded responses based on long-form input context, comprising 1,719 examples with documents up to 32k tokens requiring detailed responses that are fully grounded in provided documents
Gemini 2.5 Pro Preview 06-05 from Google currently leads the FACTS Grounding leaderboard with a score of 0.878 across 13 evaluated AI models.
What FACTS Grounding measures
FACTS Grounding is a text benchmark that evaluates large language models on factuality, grounding, and reasoning tasks. LLM Stats tracks 13 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.7, with the leader reaching 0.9.
Compare leaders on the best AI for factuality, best AI for grounding and best AI for reasoning leaderboards.
Publication
- Paper
- The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input
- Authors
- Alon Jacovi, Andrew Wang, Chris Alberti, Connie Tao, and 22 others
- Published
- arXiv
- 2501.03200
Abstract
We introduce FACTS Grounding, an online leaderboard and associated benchmark that evaluates language models' ability to generate text that is factually accurate with respect to given context in the user prompt. In our benchmark, each prompt includes a user request and a full document, with a maximum length of 32k tokens, requiring long-form responses. The long-form responses are required to be fully grounded in the provided context document while fulfilling the user request. Models are evaluated using automated judge models in two phases: (1) responses are disqualified if they do not fulfill the user request; (2) they are judged as accurate if the response is fully grounded in the provided document. The automated judge models were comprehensively evaluated against a held-out test-set to pick the best prompt template, and the final factuality score is an aggregate of multiple judge models to mitigate evaluation bias. The FACTS Grounding leaderboard will be actively maintained over time, and contains both public and private splits to allow for external participation while guarding the integrity of the leaderboard. It can be found at https://www.kaggle.com/facts-leaderboard.
Gemini 2.5 Pro Preview 06-05 leads with 87.8%, followed by Gemini 2.5 Flash at 85.3% and Gemini 2.5 Flash-Lite at 84.1%.
Progress Over Time
Interactive timeline showing model performance evolution on FACTS Grounding
FACTS Grounding Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | — | — | — | |||
| 2 | Google | — | 1.0M | $0.30 / $2.50 | ||
| 3 | Google | — | — | — | ||
| 4 | Google | — | — | — | ||
| 4 | Google | — | — | — | ||
| 6 | Google | 12B | — | — | ||
| 7 | Google | 27B | — | — | ||
| 8 | Google | — | — | — | ||
| 9 | Google | 4B | — | — | ||
| 10 | Google | — | 1.0M | $0.50 / $3.00 | ||
| 11 |  Zhipu AI | — | — | — | ||
| 12 | Google | — | 1.0M | $0.25 / $1.50 | ||
| 13 | Google | 1B | — | — |
FAQ
Common questions about FACTS Grounding.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions