# Multi-hop Question Answering on HotpotQA (score (avg@3))

Source: [Multi-hop Question Answering on HotpotQA (score (avg@3))](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-score-avg-at-3>)

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

Data updated: 2026-05-22T07:41:58.800Z

Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, specifically reporting the average score across the top 3 results.

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 | Multi-hop Question Answering |
| Dataset (including any stated split) | HotpotQA |
| Metric | Score (Avg@3) |
| 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

- [Score (Avg@3)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-score-avg-at-3.md?metric=Score%20(Avg%403)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score (Avg@3) | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-235B-A22B-Thinking | 90 | Not recorded | 6a0fe320f984739ed6739e06 |
| Qwen3-30B-A3B-Thinking + ACC | 88.5 | Not recorded | 6a0fe320f984739ed6739e06 |
| Qwen3-30B-A3B-Thinking | 87 | Not recorded | 6a0fe320f984739ed6739e06 |

### Qwen3-235B-A22B-Thinking

Score (Avg@3): 90. Result ID: 6a1008c3fbc373592c08b064.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe320f984739ed6739e06.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Baseline category":"Strong Baseline"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B-Thinking + ACC

Score (Avg@3): 88.5. Result ID: 6a1008c3fbc373592c08b063.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe320f984739ed6739e06.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe320f984739ed6739e06.md>)

Recorded evaluation configuration: {"Method category":"Our Method"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B-Thinking

Score (Avg@3): 87. Result ID: 6a1008c3fbc373592c08b062.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe320f984739ed6739e06.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Baseline category":"Base Model"}. This record does not assert independent reproduction.

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