# Question Answering on NQ 30K context

Source: [Question Answering on NQ 30K context](<https://www.sota2.com/research/sota/question-answering-on-nq-30k-context>)

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

Data updated: 2026-02-27T10:39:50.697Z

Evaluation of model performance on the NQ 30K context subset of the Natural Questions dataset for Question Answering, focusing on 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) | NQ 30K context |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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-nq-30k-context.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Mem0 | 51.1 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemOCR | 49.2 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem0 | 48.8 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemOCR | 48.8 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemAgent | 46.1 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem-α | 44.8 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemAgent | 44.3 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Qwen2.5-1M | 43.8 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem0 | 43.8 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemOCR | 43.6 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemAgent | 36.5 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemOCR | 35.9 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem0 | 34.1 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem-α | 33.6 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem-α | 26.3 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| Mem-α | 25 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| MemAgent | 20.1 | Not recorded | 697c3b09a8b01e76cc8da4a7 |
| R1-Distill Qwen | 3.9 | Not recorded | 697c3b09a8b01e76cc8da4a7 |

### Mem0

Accuracy: 51.1. Result ID: 69a1747535dfcabb00e72211.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"256"}. This record does not assert independent reproduction.

### MemOCR

Accuracy: 49.2. Result ID: 69a1747535dfcabb00e7221c.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Implementation](<https://github.com/syr-cn/MemOCR>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"1024"}. This record does not assert independent reproduction.

### Mem0

Accuracy: 48.8. Result ID: 69a1747535dfcabb00e72210.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"1024"}. This record does not assert independent reproduction.

### MemOCR

Accuracy: 48.8. Result ID: 69a1747535dfcabb00e7221d.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Implementation](<https://github.com/syr-cn/MemOCR>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"256"}. This record does not assert independent reproduction.

### MemAgent

Accuracy: 46.1. Result ID: 69a1747535dfcabb00e72218.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c71e209131cea7f569.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"1024"}. This record does not assert independent reproduction.

### Mem-α

Accuracy: 44.8. Result ID: 69a1747535dfcabb00e72214.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc91e209131cea8a773.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"1024"}. This record does not assert independent reproduction.

### MemAgent

Accuracy: 44.3. Result ID: 69a1747535dfcabb00e72219.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c71e209131cea7f569.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"256"}. This record does not assert independent reproduction.

### Qwen2.5-1M

Accuracy: 43.8. Result ID: 69a1747535dfcabb00e7220f.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bc1e209131cea6ed30.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"100K"}. This record does not assert independent reproduction.

### Mem0

Accuracy: 43.8. Result ID: 69a1747535dfcabb00e72212.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"64"}. This record does not assert independent reproduction.

### MemOCR

Accuracy: 43.6. Result ID: 69a1747535dfcabb00e7221e.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Implementation](<https://github.com/syr-cn/MemOCR>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"64"}. This record does not assert independent reproduction.

### MemAgent

Accuracy: 36.5. Result ID: 69a1747535dfcabb00e7221a.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c71e209131cea7f569.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"64"}. This record does not assert independent reproduction.

### MemOCR

Accuracy: 35.9. Result ID: 69a1747535dfcabb00e7221f.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Implementation](<https://github.com/syr-cn/MemOCR>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"16"}. This record does not assert independent reproduction.

### Mem0

Accuracy: 34.1. Result ID: 69a1747535dfcabb00e72213.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa784b1e209131cea77ad6.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"16"}. This record does not assert independent reproduction.

### Mem-α

Accuracy: 33.6. Result ID: 69a1747535dfcabb00e72215.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc91e209131cea8a773.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"256"}. This record does not assert independent reproduction.

### Mem-α

Accuracy: 26.3. Result ID: 69a1747535dfcabb00e72217.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc91e209131cea8a773.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"16"}. This record does not assert independent reproduction.

### Mem-α

Accuracy: 25. Result ID: 69a1747535dfcabb00e72216.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc91e209131cea8a773.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"64"}. This record does not assert independent reproduction.

### MemAgent

Accuracy: 20.1. Result ID: 69a1747535dfcabb00e7221b.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c71e209131cea7f569.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"16"}. This record does not assert independent reproduction.

### R1-Distill Qwen

Accuracy: 3.9. Result ID: 69a1747535dfcabb00e7220e.

[Reporting paper](<https://www.sota2.com/research/paper/697c3b09a8b01e76cc8da4a7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Memory Budget (Tokens)":"100K"}. This record does not assert independent reproduction.

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