ZeroSCROLLS/QuALITY

Llama 3.1-405B 95.2% leads since July 2024

davinci-003 69% leads

Llama 3.1-405B 95.2% leads since July 2024

Dropped

Labs’ own numbers All independent runs Include claimed scores

Models answer QuALITY multiple-choice questions about long stories zero-shot, as one task of the ZeroSCROLLS suite. Scoring is accuracy.

The ZeroSCROLLS leaderboard at zero.scrolls-benchmark.com did not answer on November 1st, 2026.

Made by: Tel Aviv University
Released: May 2023
Kind: Reasoning over long documents
Level: Everyday
Scored: Checked automatically
Answers: Multiple choice
Tasks: All public

Strongest model tested: Llama 3.1-405B #162 on the capability index
Last in a launch post: July 2024, dropped after it saturated
Last model added: November 2024
Scores refreshed: November 12th, 2026

In the authors’ words

We introduce ZeroSCROLLS, a zero-shot benchmark for natural language understanding over long texts, which contains only test and small validation sets, without training data. We adapt six tasks from the SCROLLS benchmark, and add four new datasets, including two novel information fusing tasks, such as aggregating the percentage of positive reviews. Using ZeroSCROLLS, we conduct a comprehensive evaluation of both open-source and closed large language models, finding that Claude outperforms ChatGPT, and that GPT-4 achieves the highest average score. However, there is still room for improvement on multiple open challenges in ZeroSCROLLS, such as aggregation tasks, where models struggle to pass the naive baseline. As the state of the art is a moving target, we invite researchers to evaluate their ideas on the live ZeroSCROLLS leaderboard.

Abstract of ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding (arXiv:2305.14196, CC0)

Models scored in lab cards

Launch post lists it, from 1 lab

System cards report it, from 1 lab

Llama 3.1-405B leads with 95.2% among models released by July 2024

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.

davinci-003 leads with 69% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

Llama 3.1-405B leads with 95.2%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

Bars Table

The newest model with a score here came out in July 2024, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Source: Labs’ model cards

69.0 davinci-003

1 davinci-003 4096 input token limit 69%

Source: Official ZeroSCROLLS/QuALITY leaderboard

1 Llama 3.1-405B 95.2%
2 Llama 3.1-70B 90.5%
3 Llama 3.1-8B 81%
4 davinci-003 4096 input token limit 69%

Sources: Labs’ model cards and official ZeroSCROLLS/QuALITY leaderboard

#	Model	Score	Date	Source
1	Llama 3.1-405B	95.2%	Jul 2024	Lab model card
2	Llama 3.1-70B	90.5%	Nov 2024	Lab model card
3	Llama 3.1-8B	81%	Nov 2024	Lab model card

#	Model	Score	Setting	Date	Source
1	davinci-003	69%	4096 input token limit	Nov 2022	Official leaderboard

#	Model	Score	Setting	Date	Source
1	Llama 3.1-405B	95.2%		Jul 2024	Lab model card
2	Llama 3.1-70B	90.5%		Nov 2024	Lab model card
3	Llama 3.1-8B	81%		Nov 2024	Lab model card
4	davinci-003	69%	4096 input token limit	Nov 2022	Official leaderboard

The benchmark's own leaderboard has 8 entries, 1 of them models we track. Switch the scores above to rank them together.

Number one over time Number one over time 2 models have held number one with claims included since its release in May 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Meta’s own number for Llama 3.1-405B passed 85% in July 2024

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official ZeroSCROLLS/QuALITY leaderboard and labs’ model cards

Labs dropped it from launch posts once the best score passed 85%

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.

3 system cards report it, from 1 lab

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
Nov 23, 2024	Llama 3.1-8B technical report	81	ZeroSCROLLS/QuALITY, exact match, validation set, post-trained (Table 2, Table 21)	Capabilities
Nov 23, 2024	Llama 3.1-70B technical report	90.5	ZeroSCROLLS/QuALITY, exact match, validation set, post-trained (Table 2, Table 21)	Capabilities
Nov 23, 2024	Llama 3.1-405B technical report	95.2	ZeroSCROLLS/QuALITY, exact match, validation set, post-trained (Table 2, Table 21)	Capabilities