# Question Answering on LongMemEval 500 questions

Source: [Question Answering on LongMemEval 500 questions](<https://www.sota2.com/research/sota/question-answering-on-longmemeval-500-questions>)

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

Data updated: 2026-05-06T07:55:19.522Z

Evaluation of Question Answering performance on the 500-question subset of the LongMemEval dataset, measured by QA accuracy.

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) | LongMemEval 500 questions |
| Metric | QA Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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

- [QA Accuracy](<https://www.sota2.com/research/sota/question-answering-on-longmemeval-500-questions.md?metric=QA%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | QA Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Diagnostic-conditional | 61.4 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Diagnostic-conditional | 60 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Best unconditional | 59.8 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Best unconditional | 59.8 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Intact | 58.6 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Best unconditional | 58.2 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Diagnostic-conditional | 57.4 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Intact | 57.4 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Intact | 56.2 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Best unconditional | 34.4 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Diagnostic-conditional | 34.4 | Not recorded | 69facb35c0f56ed84308a4f0 |
| Intact | 34 | Not recorded | 69facb35c0f56ed84308a4f0 |

### Diagnostic-conditional

QA Accuracy: 61.4. Result ID: 69faf26947f34ce924dda109.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"8B"}. This record does not assert independent reproduction.

### Diagnostic-conditional

QA Accuracy: 60. Result ID: 69faf26947f34ce924dda10c.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"14B"}. This record does not assert independent reproduction.

### Best unconditional

QA Accuracy: 59.8. Result ID: 69faf26947f34ce924dda108.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"8B"}. This record does not assert independent reproduction.

### Best unconditional

QA Accuracy: 59.8. Result ID: 69faf26947f34ce924dda10b.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"14B"}. This record does not assert independent reproduction.

### Intact

QA Accuracy: 58.6. Result ID: 69faf26947f34ce924dda10a.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"14B"}. This record does not assert independent reproduction.

### Best unconditional

QA Accuracy: 58.2. Result ID: 69faf26947f34ce924dda105.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"4B"}. This record does not assert independent reproduction.

### Diagnostic-conditional

QA Accuracy: 57.4. Result ID: 69faf26947f34ce924dda106.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"4B"}. This record does not assert independent reproduction.

### Intact

QA Accuracy: 57.4. Result ID: 69faf26947f34ce924dda107.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"8B"}. This record does not assert independent reproduction.

### Intact

QA Accuracy: 56.2. Result ID: 69faf26947f34ce924dda104.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"4B"}. This record does not assert independent reproduction.

### Best unconditional

QA Accuracy: 34.4. Result ID: 69faf26947f34ce924dda102.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"0.6B"}. This record does not assert independent reproduction.

### Diagnostic-conditional

QA Accuracy: 34.4. Result ID: 69faf26947f34ce924dda103.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"0.6B"}. This record does not assert independent reproduction.

### Intact

QA Accuracy: 34. Result ID: 69faf26947f34ce924dda101.

[Reporting paper](<https://www.sota2.com/research/paper/69facb35c0f56ed84308a4f0.md>)

Recorded evaluation configuration: {"Scale":"0.6B"}. This record does not assert independent reproduction.

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