SQuALITY
Phi-3.5-mini 24.3% leads since Aug 2024 Dropped Models write question-focused summaries of public-domain short stories. Outputs are scored against human-written reference summaries with ROUGE.
In the authors’ words
Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries – which are nearly always in difficult-to-work-with technical domains – or by using approximate heuristics to extract them from everyday text – which frequently yields unfaithful summaries. In this work, we turn to a slower but more straightforward approach to developing summarization benchmark data: We hire highly-qualified contractors to read stories and write original summaries from scratch. To amortize reading time, we collect five summaries per document, with the first giving an overview and the subsequent four addressing specific questions. We use this protocol to collect SQuALITY, a dataset of question-focused summaries built on the same public-domain short stories as the multiple-choice dataset QuALITY (Pang et al., 2021). Experiments with state-of-the-art summarization systems show that our dataset is challenging and that existing automatic evaluation metrics are weak indicators of quality.
- Level
- School Students, from grade school to high school
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Phi-3.5-mini leads with 24.3% among models released by Feb 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Feb 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Phi-3.5-mini 24.3%
- 2 Phi-3.5-MoE 24.1%
- 3 Phi-4 Mini 22.8%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Phi-3.5-mini | 24.3% | Aug 2024 | Model card | |
| 2 | Phi-3.5-MoE | 24.1% | Aug 2024 | Model card | |
| 3 | Phi-4 Mini | 22.8% | Mar 2025 | Model card |
2 models have held number one since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No launch post has listed it since Aug 2024
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 20 Aug 2024 | Phi-3.5-MoE | 24.1 | SQuALITY |
6 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 3 Mar 2025 | Phi-4 Mini technical report | 22.8 | SQuALITY (0-shot) (Table 7) | Capabilities |
| 23 Nov 2024 |  Llama 3.1-8B technical report | 15.3 | ZeroSCROLLS/SQuALITY, ROUGE-L, validation set, post-trained (Table 21) | Capabilities |
| 23 Nov 2024 | Llama 3.1-70B technical report | 16.4 | ZeroSCROLLS/SQuALITY, ROUGE-L, validation set, post-trained (Table 21) | Capabilities |
| 23 Nov 2024 | Llama 3.1-405B technical report | 15.4 | ZeroSCROLLS/SQuALITY, ROUGE-L, validation set, post-trained (Table 21) | Capabilities |
| 30 Aug 2024 | Phi-3.5-MoE technical report | 24.1 | SQuALITY (Table 3) | Capabilities |
| 30 Aug 2024 | Phi-3.5-mini technical report | 24.3 | SQuALITY (Table 3) | Capabilities |
More in Long context
- MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens. Muse Spark 1.3 98.5%
- LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy. Beam 1.0 66.9%
- GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 100%
- OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin.
K-EXAONE 2.0 94.4% - CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
- AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key.
Step 5 Preview 88.3%