reasoning benchmark
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
Updated Aug 11, 2026
Models13
Model coverage13
MetricScore
EvidenceC
FACTS Grounding Ranking
Higher score ranks better on this benchmark.
| 01 | GO | 87.8% | 100.0% | 13 | C | |
| 02 | GO | 85.3% | 91.7% | 13 | C | |
| 03 | GO | 84.1% | 83.3% | 13 | C | |
| 04 | GO | 83.6% | 75.0% | 13 | C | |
| 05 | GO | 83.6% | 66.7% | 13 | C | |
| 06 | GO | 75.8% | 58.3% | 13 | C | |
| 07 | GO | 74.9% | 50.0% | 13 | C | |
| 08 | GO | 70.5% | 41.7% | 13 | C | |
| 09 | GO | 70.1% | 33.3% | 13 | C | |
| 10 | GO | 61.9% | 25.0% | 13 | C | |
| 11 | ZA | 58.6% | 16.7% | 13 | C | |
| 12 | GO | 40.6% | 8.3% | 13 | C | |
| 13 | GO | 36.4% | 0.0% | 13 | C |
FACTS Grounding Score Distribution
A closer view of the leading scores on this benchmark.
FACTS Grounding Highlights
The leading models and scores on this benchmark.
What is FACTS Grounding?
What FACTS Grounding measures and how its scores work.
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
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of C.
- Family
- FACTS Grounding
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- facts-grounding|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FACTS Grounding.
Which model scores highest on FACTS Grounding?
Gemini 2.5 Pro Preview 06-05 is currently ranked first with 87.8%.
What does FACTS Grounding measure?
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
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
13 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.