# End-to-end Question Answering on HotpotQA ANCE

Source: [End-to-end Question Answering on HotpotQA ANCE](<https://www.sota2.com/research/sota/end-to-end-question-answering-on-hotpotqa-ance>)

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

Data updated: 2026-02-26T05:49:37.441Z

Evaluation of model performance on the HotpotQA ANCE setting for end-to-end question answering, measured using MAP@10 and ACCL.

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 | End-to-end Question Answering |
| Dataset (including any stated split) | HotpotQA ANCE |
| Metric | MAP@10 |
| 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

- [MAP@10](<https://www.sota2.com/research/sota/end-to-end-question-answering-on-hotpotqa-ance.md?metric=MAP%4010>): Higher is better; unit: PERCENT.

- [ACCL](<https://www.sota2.com/research/sota/end-to-end-question-answering-on-hotpotqa-ance.md?metric=ACCL>): Higher is better; unit: PERCENT.

- [Delta ACCL](<https://www.sota2.com/research/sota/end-to-end-question-answering-on-hotpotqa-ance.md?metric=Delta%20ACCL>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MAP@10 | Result date | Report paper |
| --- | --- | --- | --- |
| ACQO | 49.6 | Not recorded | 697c3af1a8b01e76cc8da3a3 |
| ConvSearch-R1 | 44.4 | Not recorded | 697c3af1a8b01e76cc8da3a3 |
| Raw Query | 34.8 | Not recorded | 697c3af1a8b01e76cc8da3a3 |

### ACQO

MAP@10: 49.6. Result ID: 69961b7d5698665ec45b8eff.

[Reporting paper](<https://www.sota2.com/research/paper/697c3af1a8b01e76cc8da3a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3af1a8b01e76cc8da3a3.md>)

Recorded evaluation configuration: {"Reader Model":"Qwen2.5-7B-Instruct","Evaluation Judge":"DeepSeek-R1","Retriever":"ANCE","Top-k Context":"10"}. This record does not assert independent reproduction.

### ConvSearch-R1

MAP@10: 44.4. Result ID: 69961b7d5698665ec45b8efe.

[Reporting paper](<https://www.sota2.com/research/paper/697c3af1a8b01e76cc8da3a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b461e209131cea87749.md>)

Recorded evaluation configuration: {"Reader Model":"Qwen2.5-7B-Instruct","Evaluation Judge":"DeepSeek-R1","Retriever":"ANCE","Top-k Context":"10"}. This record does not assert independent reproduction.

### Raw Query

MAP@10: 34.8. Result ID: 69961b7d5698665ec45b8efd.

[Reporting paper](<https://www.sota2.com/research/paper/697c3af1a8b01e76cc8da3a3.md>)

Recorded evaluation configuration: {"Reader Model":"Qwen2.5-7B-Instruct","Evaluation Judge":"DeepSeek-R1","Retriever":"ANCE","Top-k Context":"10"}. This record does not assert independent reproduction.

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