summarization benchmark
GovReport
A long document summarization dataset consisting of reports from government research agencies including Congressional Research Service and U.S. Government Accountability Office, with significantly longer documents and summaries than other datasets.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
GovReport leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 26.4% | 100.0% | 2 | C | |
| 2 | MI | 25.9% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
GovReport highlights
The top published results on this benchmark's own scale.
What is GovReport?
Definition and scoring fields from the benchmark registry.
A long document summarization dataset consisting of reports from government research agencies including Congressional Research Service and U.S. Government Accountability Office, with significantly longer documents and summaries than other datasets.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- GovReport
- Modality
- text
- Primary category
- summarization
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- govreport|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about GovReport.
Which model scores highest on GovReport?
Phi-3.5-MoE-instruct is currently ranked first with 26.4%.
What does GovReport measure?
A long document summarization dataset consisting of reports from government research agencies including Congressional Research Service and U.S. Government Accountability Office, with significantly longer documents and summaries than other datasets.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.