# Conversational Question Answering on CoQA without human rewrites v1.0 (test)

Source: [Conversational Question Answering on CoQA without human rewrites v1.0 (test)](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test>)

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

Data updated: 2026-02-26T05:54:29.642Z

Evaluation of model performance on the test split of the CoQA dataset, specifically excluding human rewrites (v1.0), for Conversational Question Answering, reporting domain-specific F1 scores.

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 | Conversational Question Answering |
| Dataset (including any stated split) | CoQA without human rewrites v1.0 (test) |
| Metric | Overall F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Overall F1](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md?metric=Overall%20F1>): Higher is better; unit: PERCENT.

- [Child F1](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md?metric=Child%20F1>): Higher is better; unit: PERCENT.

- [Literary F1](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md?metric=Literary%20F1>): Higher is better; unit: PERCENT.

- [M&H F1](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md?metric=M%26H%20F1>): Higher is better; unit: PERCENT.

- [News F1](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md?metric=News%20F1>): Higher is better; unit: PERCENT.

- [Wiki F1](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md?metric=Wiki%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall F1 | Result date | Report paper |
| --- | --- | --- | --- |
| EXCORD (RoBERTa) | 83.4 | Not recorded | 68fa6a3f1e209131cea26ff4 |
| RoBERTa (End-to-End) | 82.8 | Not recorded | 68fa6a3f1e209131cea26ff4 |
| RoBERTa (Pipeline) | 81.1 | Not recorded | 68fa6a3f1e209131cea26ff4 |
| EXCORD (BERT) | 78.8 | Not recorded | 68fa6a3f1e209131cea26ff4 |
| BERT (End-to-End) | 78.3 | Not recorded | 68fa6a3f1e209131cea26ff4 |
| BERT (Pipeline) | 76.1 | Not recorded | 68fa6a3f1e209131cea26ff4 |

### EXCORD (RoBERTa)

Overall F1: 83.4. Result ID: 698e23e4ffc3901de09b1bf7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Implementation](<https://github.com/dmis-lab/excord>)

Recorded evaluation configuration: {"QA model":"RoBERTa","Approach":"Ours"}. This record does not assert independent reproduction.

### RoBERTa (End-to-End)

Overall F1: 82.8. Result ID: 698e23e4ffc3901de09b1bf5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"QA model":"RoBERTa","Approach":"End-to-End"}. This record does not assert independent reproduction.

### RoBERTa (Pipeline)

Overall F1: 81.1. Result ID: 698e23e4ffc3901de09b1bf6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"QA model":"RoBERTa","Approach":"Pipeline"}. This record does not assert independent reproduction.

### EXCORD (BERT)

Overall F1: 78.8. Result ID: 698e23e4ffc3901de09b1bf4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Implementation](<https://github.com/dmis-lab/excord>)

Recorded evaluation configuration: {"QA model":"BERT","Approach":"Ours"}. This record does not assert independent reproduction.

### BERT (End-to-End)

Overall F1: 78.3. Result ID: 698e23e4ffc3901de09b1bf2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"QA model":"BERT","Approach":"End-to-End"}. This record does not assert independent reproduction.

### BERT (Pipeline)

Overall F1: 76.1. Result ID: 698e23e4ffc3901de09b1bf3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"QA model":"BERT","Approach":"Pipeline"}. This record does not assert independent reproduction.

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