# Long-context Question Answering on MuSiQue (LongBench test set)

Source: [Long-context Question Answering on MuSiQue (LongBench test set)](<https://www.sota2.com/research/sota/long-context-question-answering-on-musique-longbench-test-set>)

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

Data updated: 2026-07-08T07:26:42.150Z

Evaluation of Long-context Question Answering performance specifically on the MuSiQue dataset subset within the LongBench test suite, utilizing String Match, F1, ROUGE-L, and BERTScore metrics.

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) | MuSiQue LongBench (test) |
| Metric | String Match |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [String Match](<https://www.sota2.com/research/sota/long-context-question-answering-on-musique-longbench-test-set.md?metric=String%20Match>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/long-context-question-answering-on-musique-longbench-test-set.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/long-context-question-answering-on-musique-longbench-test-set.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

- [BERTScore](<https://www.sota2.com/research/sota/long-context-question-answering-on-musique-longbench-test-set.md?metric=BERTScore>): Higher is better; unit: PERCENT.

## Recorded results

| Method | String Match | Result date | Report paper |
| --- | --- | --- | --- |
| MemDefrag | 20 | Not recorded | 6a4dd9854da6617fe9198aa6 |
| M+ | 19.5 | Not recorded | 6a4dd9854da6617fe9198aa6 |
| MemoryLLM | 16 | Not recorded | 6a4dd9854da6617fe9198aa6 |

### MemDefrag

String Match: 20. Result ID: 6a4dfba260b88bb339d7155b.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9854da6617fe9198aa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4dd9854da6617fe9198aa6.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B","Max Length":"16,384 tokens","Top-K":"2"}. This record does not assert independent reproduction.

### M+

String Match: 19.5. Result ID: 6a4dfba260b88bb339d7155a.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9854da6617fe9198aa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79071e209131cea7bc6b.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B","Max Length":"16,384 tokens"}. This record does not assert independent reproduction.

### MemoryLLM

String Match: 16. Result ID: 6a4dfba260b88bb339d71559.

[Reporting paper](<https://www.sota2.com/research/paper/6a4dd9854da6617fe9198aa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73541e209131cea5bdeb.md>)

Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B","Max Length":"16,384 tokens"}. This record does not assert independent reproduction.

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