# Question Answering on NQ SYNTH

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

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

Data updated: 2026-04-21T07:55:58.627Z

Evaluation of model performance on the NQ SYNTH dataset for Question Answering, measured using 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 SYNTH |
| 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-synth.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| NWCAD | 79 | Not recorded | 69e704667d0172140ec7eb3c |
| AdaCAD | 76.38 | Not recorded | 69e704667d0172140ec7eb3c |
| AdaCAD | 72.8 | Not recorded | 69e704667d0172140ec7eb3c |
| NWCAD | 71.8 | Not recorded | 69e704667d0172140ec7eb3c |
| CoCoA | 71.62 | Not recorded | 69e704667d0172140ec7eb3c |
| With-context | 70.7 | Not recorded | 69e704667d0172140ec7eb3c |
| NWCAD | 70 | Not recorded | 69e704667d0172140ec7eb3c |
| AdaCAD | 69.8 | Not recorded | 69e704667d0172140ec7eb3c |
| With-context | 69.6 | Not recorded | 69e704667d0172140ec7eb3c |
| With-context | 69.5 | Not recorded | 69e704667d0172140ec7eb3c |
| CAD | 66.62 | Not recorded | 69e704667d0172140ec7eb3c |
| CAD | 64.8 | Not recorded | 69e704667d0172140ec7eb3c |
| CoCoA | 64.4 | Not recorded | 69e704667d0172140ec7eb3c |
| CAD | 64.3 | Not recorded | 69e704667d0172140ec7eb3c |
| CoCoA | 58.9 | Not recorded | 69e704667d0172140ec7eb3c |
| Baseline | 25.5 | Not recorded | 69e704667d0172140ec7eb3c |
| Baseline | 20.5 | Not recorded | 69e704667d0172140ec7eb3c |
| Baseline | 19.25 | Not recorded | 69e704667d0172140ec7eb3c |

### NWCAD

Accuracy: 79. Result ID: 69e72d8c47f34ce924cd300d.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-70B"}. This record does not assert independent reproduction.

### AdaCAD

Accuracy: 76.38. Result ID: 69e72d8c47f34ce924cd300b.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78411e209131cea776f7.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-70B"}. This record does not assert independent reproduction.

### AdaCAD

Accuracy: 72.8. Result ID: 69e72d8c47f34ce924cd3011.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78411e209131cea776f7.md>)

Recorded evaluation configuration: {"Model":"Ministral-3-8B"}. This record does not assert independent reproduction.

### NWCAD

Accuracy: 71.8. Result ID: 69e72d8c47f34ce924cd3013.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Ministral-3-8B"}. This record does not assert independent reproduction.

### CoCoA

Accuracy: 71.62. Result ID: 69e72d8c47f34ce924cd300c.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7add1e209131cea8594e.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-70B"}. This record does not assert independent reproduction.

### With-context

Accuracy: 70.7. Result ID: 69e72d8c47f34ce924cd300f.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Ministral-3-8B"}. This record does not assert independent reproduction.

### NWCAD

Accuracy: 70. Result ID: 69e72d8c47f34ce924cd3007.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### AdaCAD

Accuracy: 69.8. Result ID: 69e72d8c47f34ce924cd3005.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78411e209131cea776f7.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### With-context

Accuracy: 69.6. Result ID: 69e72d8c47f34ce924cd3003.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### With-context

Accuracy: 69.5. Result ID: 69e72d8c47f34ce924cd3009.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-70B"}. This record does not assert independent reproduction.

### CAD

Accuracy: 66.62. Result ID: 69e72d8c47f34ce924cd300a.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6e1e209131cea45813.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-70B"}. This record does not assert independent reproduction.

### CAD

Accuracy: 64.8. Result ID: 69e72d8c47f34ce924cd3010.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6e1e209131cea45813.md>)

Recorded evaluation configuration: {"Model":"Ministral-3-8B"}. This record does not assert independent reproduction.

### CoCoA

Accuracy: 64.4. Result ID: 69e72d8c47f34ce924cd3006.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7add1e209131cea8594e.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### CAD

Accuracy: 64.3. Result ID: 69e72d8c47f34ce924cd3004.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6e1e209131cea45813.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### CoCoA

Accuracy: 58.9. Result ID: 69e72d8c47f34ce924cd3012.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7add1e209131cea8594e.md>)

Recorded evaluation configuration: {"Model":"Ministral-3-8B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 25.5. Result ID: 69e72d8c47f34ce924cd3002.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 20.5. Result ID: 69e72d8c47f34ce924cd300e.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Ministral-3-8B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 19.25. Result ID: 69e72d8c47f34ce924cd3008.

[Reporting paper](<https://www.sota2.com/research/paper/69e704667d0172140ec7eb3c.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-70B"}. This record does not assert independent reproduction.

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