# Long-context Question Answering on QuALITY

Source: [Long-context Question Answering on QuALITY](<https://www.sota2.com/research/sota/long-context-question-answering-on-quality>)

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

Data updated: 2026-05-11T09:24:08.254Z

Evaluation of model performance on the QuALITY dataset specifically focusing on long-context question answering capabilities, measured by 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 | Long-context Question Answering |
| Dataset (including any stated split) | QuALITY |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/long-context-question-answering-on-quality.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen2.5 | 73.63 | Not recorded | 68fa7c421e209131cea8d35b |
| SpikingBrain-76B | 69.56 | Not recorded | 68fa7c421e209131cea8d35b |
| Llama3 | 66.25 | Not recorded | 68fa7c421e209131cea8d35b |
| SpikingBrain-7B | 60.12 | Not recorded | 68fa7c421e209131cea8d35b |
| Mixtral | 51.34 | Not recorded | 68fa7c421e209131cea8d35b |

### Qwen2.5

Accuracy: 73.63. Result ID: 6a01a01d47f34ce924e3c946.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: {"Parameters":"7B","Complexity Type":"Quadratic","Evaluation Framework":"vLLM","Evaluation Method":"generation-based","Chain-of-thought (CoT) Usage":"non-CoT"}. This record does not assert independent reproduction.

### SpikingBrain-76B

Accuracy: 69.56. Result ID: 6a01a01d47f34ce924e3c944.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

Recorded evaluation configuration: {"Parameters":"12B/76B","Complexity Type":"Hybrid","Evaluation Framework":"vLLM","Evaluation Method":"generation-based","Chain-of-thought (CoT) Usage":"non-CoT"}. This record does not assert independent reproduction.

### Llama3

Accuracy: 66.25. Result ID: 6a01a01d47f34ce924e3c945.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Parameters":"8B","Complexity Type":"Quadratic","Evaluation Framework":"vLLM","Evaluation Method":"generation-based","Chain-of-thought (CoT) Usage":"non-CoT"}. This record does not assert independent reproduction.

### SpikingBrain-7B

Accuracy: 60.12. Result ID: 6a01a01d47f34ce924e3c943.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

Recorded evaluation configuration: {"Parameters":"7B","Complexity Type":"Linear","Evaluation Framework":"vLLM","Evaluation Method":"generation-based","Chain-of-thought (CoT) Usage":"non-CoT"}. This record does not assert independent reproduction.

### Mixtral

Accuracy: 51.34. Result ID: 6a01a01d47f34ce924e3c947.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c421e209131cea8d35b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d01e209131cea5317b.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Parameters":"13B/47B","Complexity Type":"Quadratic","Evaluation Framework":"vLLM","Evaluation Method":"generation-based","Chain-of-thought (CoT) Usage":"non-CoT"}. This record does not assert independent reproduction.

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