# Question Answering on QuALITY ZeroSCROLLS leaderboard (test)

Source: [Question Answering on QuALITY ZeroSCROLLS leaderboard (test)](<https://www.sota2.com/research/sota/question-answering-on-quality-zeroscrolls-leaderboard-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:29:44.096Z

Evaluation of model performance on the test split of the QuALITY ZeroSCROLLS leaderboard for Question Answering.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Question Answering |
| Dataset (including any stated split) | QuALITY ZeroSCROLLS leaderboard (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/question-answering-on-quality-zeroscrolls-leaderboard-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ChatGPT (ER) | 72.8 | Not recorded | 68fa73771e209131cea5cb67 |
| ChatGPT (R) | 70.8 | Not recorded | 68fa73771e209131cea5cb67 |
| Llama2-70B (R)\* | 70.3 | Not recorded | 68fa73771e209131cea5cb67 |
| ChatGPT\* | 66.6 | Not recorded | 68fa73771e209131cea5cb67 |

### ChatGPT (ER)

Accuracy: 72.8. Result ID: 6992eeae3a6c314849127473.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb67.md>)

Recorded evaluation configuration: {"Retrieval method":"Enhanced Retrieval (ER) with NARCO","Context limit":"1.5k"}. This record does not assert independent reproduction.

### ChatGPT (R)

Accuracy: 70.8. Result ID: 6992eeae3a6c314849127472.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb67.md>)

Recorded evaluation configuration: {"Retrieval method":"Baseline (R)","Context limit":"1.5k"}. This record does not assert independent reproduction.

### Llama2-70B (R)\*

Accuracy: 70.3. Result ID: 6992eeae3a6c314849127471.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fa1e209131cea53df2.md>)

Recorded evaluation configuration: {"Retrieval method":"Baseline (R)","Context limit":"1.5k","Reported by":"Xu et al. (2024)"}. This record does not assert independent reproduction.

### ChatGPT\*

Accuracy: 66.6. Result ID: 6992eeae3a6c314849127470.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71781e209131cea5172c.md>)

Recorded evaluation configuration: {"source":"ZeroSCROLLS organizers"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
