language benchmark
SQuALITY Leaderboard
SQuALITY is a long-document summarization dataset based on public-domain short stories of 3000-6000 words, with one overview summary and four question-focused summaries per document.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
SQuALITY Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score24.30% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score24.10% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelAM Nova ProAmazon | Score19.80% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelAMNova LiteAmazon | Score19.20% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelAMNova MicroAmazon | Score18.80% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
SQuALITY Highlights
The leading models and scores on this benchmark.
SQuALITY Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for SQuALITY
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is SQuALITY?
What SQuALITY measures and how its scores work.
SQuALITY (Summarization-format QUestion Answering with Long Input Texts, Yes!) is a language benchmark dataset for long-document summarization.
SQuALITY measures summarization performance using the metric Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- SQuALITY
- Modality
- text
- Primary category
- language
- 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 SQuALITY.
Which model scores highest on SQuALITY?
Phi-3.5-mini-instruct is currently ranked first with 24.30%.
What are the top three models on SQuALITY?
The current leaders are Phi-3.5-mini-instruct (24.30%), Phi-3.5-MoE-instruct (24.10%), and Nova Pro (19.80%).
Which SQuALITY model has the lowest official input price?
Nova Micro has the lowest matched official input price at $0.04 input / $0.14 output per 1M tokens.
Which models are fastest among SQuALITY results?
The fastest matched records are Phi-3.5-mini-instruct (23.00 tok/s via Azure).
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.