# Question Answering on MuSiQue (R@1, R@5, R@10, @adaptive)

Source: [Question Answering on MuSiQue (R@1, R@5, R@10, @adaptive)](<https://www.sota2.com/research/sota/question-answering-on-musique-r-at-1-r-at-5-r-at-10-at-adaptive>)

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

Data updated: 2026-03-26T13:27:20.502Z

Evaluation of model performance on the MuSiQue dataset for Question Answering tasks, measured using Recall at K metrics (R@1, R@5, R@10) and an adaptive metric.

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) | MuSiQue |
| Metric | R@1 |
| Unit | SCALAR |
| 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

- [R@1](<https://www.sota2.com/research/sota/question-answering-on-musique-r-at-1-r-at-5-r-at-10-at-adaptive.md?metric=R%401>): Higher is better; unit: SCALAR.

- [R@5](<https://www.sota2.com/research/sota/question-answering-on-musique-r-at-1-r-at-5-r-at-10-at-adaptive.md?metric=R%405>): Higher is better; unit: SCALAR.

- [R@10](<https://www.sota2.com/research/sota/question-answering-on-musique-r-at-1-r-at-5-r-at-10-at-adaptive.md?metric=R%4010>): Higher is better; unit: SCALAR.

- [Adaptive Score](<https://www.sota2.com/research/sota/question-answering-on-musique-r-at-1-r-at-5-r-at-10-at-adaptive.md?metric=Adaptive%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| KaLMv2 + Qwen3-235B | 1.988 | Not recorded | 69c4bd600636e5bf4afc7404 |
| KaLMv2 + Llama3.3 | 1.895 | Not recorded | 69c4bd600636e5bf4afc7404 |
| KaLMv2 + Qwen3-235B | 1.801 | Not recorded | 69c4bd600636e5bf4afc7404 |
| KaLMv2 + Llama3.3 | 1.704 | Not recorded | 69c4bd600636e5bf4afc7404 |

### KaLMv2 + Qwen3-235B

R@1: 1.988. Result ID: 69c533c547f34ce924aebe80.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd600636e5bf4afc7404.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c241e209131cea8cab6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-235B","Reranking":"False"}. This record does not assert independent reproduction.

### KaLMv2 + Llama3.3

R@1: 1.895. Result ID: 69c533c547f34ce924aebe83.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd600636e5bf4afc7404.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c241e209131cea8cab6.md>)

Recorded evaluation configuration: {"Backbone":"Llama3.3","Reranking":"True"}. This record does not assert independent reproduction.

### KaLMv2 + Qwen3-235B

R@1: 1.801. Result ID: 69c533c547f34ce924aebe81.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd600636e5bf4afc7404.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c241e209131cea8cab6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-235B","Reranking":"True"}. This record does not assert independent reproduction.

### KaLMv2 + Llama3.3

R@1: 1.704. Result ID: 69c533c547f34ce924aebe82.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd600636e5bf4afc7404.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c241e209131cea8cab6.md>)

Recorded evaluation configuration: {"Backbone":"Llama3.3","Reranking":"False"}. This record does not assert independent reproduction.

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