Benchmark
SQuALITY Benchmark
What is SQuALITY?
SQuALITY (Summarization-format QUestion Answering with Long Input Texts, Yes!) is a long-document summarization dataset built by hiring highly-qualified…
- Modality
- text
- Evaluates
- long context, summarization, language
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 5
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/squality?top_n=500
SQuALITY results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Nova Lite | Amazon | 0.192 | 2024-11-20 | evidence |
| Nova Micro | Amazon | 0.188 | 2024-11-20 | evidence |
| Nova Pro | Amazon | 0.198 | 2024-11-20 | evidence |
| Phi-3.5-mini-instruct | Microsoft | 0.243 | 2024-08-23 | evidence |
| Phi-3.5-MoE-instruct | Microsoft | 0.241 | 2024-08-23 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.