reasoning benchmark
FACTS Grounding Leaderboard
FACTS Grounding evaluates language models on generating factually accurate, well-grounded responses from long-form input contexts.
Updated Sep 5, 2026
Models13
Model coverage13
MetricScore
EvidenceC
FACTS Grounding Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score87.80% | Percentile100.00% | Participants13 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score85.30% | Percentile91.67% | Participants13 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score84.10% | Percentile83.33% | Participants13 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score83.60% | Percentile75.00% | Participants13 | EvidenceC | Evaluated |
| Rank05 | ModelGO | Score83.60% | Percentile66.67% | Participants13 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score75.80% | Percentile58.33% | Participants13 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score74.90% | Percentile50.00% | Participants13 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score70.50% | Percentile41.67% | Participants13 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score70.10% | Percentile33.33% | Participants13 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score61.90% | Percentile25.00% | Participants13 | EvidenceC | Evaluated |
| Rank11 | ModelZA | Score58.60% | Percentile16.67% | Participants13 | EvidenceC | Evaluated |
| Rank12 | ModelGO | Score40.60% | Percentile8.33% | Participants13 | EvidenceC | Evaluated |
| Rank13 | ModelGO | Score36.40% | Percentile0.00% | Participants13 | EvidenceC | Evaluated |
FACTS Grounding Highlights
The leading models and scores on this benchmark.
FACTS Grounding Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FACTS Grounding
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FACTS Grounding?
What FACTS Grounding measures and how its scores work.
FACTS Grounding is a reasoning benchmark comprising 1,719 examples with documents up to 32k tokens that require detailed responses grounded in the provided documents.
It measures the Score ratio for factual accuracy and grounding of responses based on the 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
- No
- Evaluation key
- overall
LLM Stats. 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 87.80%.
What are the top three models on FACTS Grounding?
The current leaders are Gemini 2.5 Pro Preview 06-05 (87.80%), Gemini 2.5 Flash (85.30%), and Gemini 2.5 Flash-Lite (84.10%).
Which FACTS Grounding model has the lowest official input price?
Gemini 2.5 Flash-Lite has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among FACTS Grounding results?
The fastest matched records are Gemini 2.0 Flash (183.00 tok/s via Google), Gemini 3 Flash (124.32 tok/s via Google), and Gemini 3 Pro (90.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.