# Question Response Pairing on BBAI 19 agents 1.0 (test)

Source: [Question Response Pairing on BBAI 19 agents 1.0 (test)](<https://www.sota2.com/research/sota/question-response-pairing-on-bbai-19-agents-1-0-test>)

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

Data updated: 2026-02-26T05:28:10.196Z

Evaluation of model performance on the test split of the BBAI 19 agents 1.0 dataset for Question Response Pairing, reporting Accuracy.

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 Response Pairing |
| Dataset (including any stated split) | BBAI 19 agents 1.0 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/question-response-pairing-on-bbai-19-agents-1-0-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MARS | 83.55 | Not recorded | 68fa6bf91e209131cea315a3 |
| USE QA | 71.66 | Not recorded | 68fa6bf91e209131cea315a3 |
| USE | 64.42 | Not recorded | 68fa6bf91e209131cea315a3 |
| Roberta | 61.88 | Not recorded | 68fa6bf91e209131cea315a3 |
| BM25 | 59.94 | Not recorded | 68fa6bf91e209131cea315a3 |
| Bert | 59.1 | Not recorded | 68fa6bf91e209131cea315a3 |
| Roberta+STS | 56.82 | Not recorded | 68fa6bf91e209131cea315a3 |
| Electra | 52.86 | Not recorded | 68fa6bf91e209131cea315a3 |
| Google | 48.06 | Not recorded | 68fa6bf91e209131cea315a3 |
| Alexa | 44.09 | Not recorded | 68fa6bf91e209131cea315a3 |
| USE | 43.59 | Not recorded | 68fa6bf91e209131cea315a3 |
| Roberta+STS | 36.67 | Not recorded | 68fa6bf91e209131cea315a3 |
| Houndify | 32.04 | Not recorded | 68fa6bf91e209131cea315a3 |
| BM25 | 23.69 | Not recorded | 68fa6bf91e209131cea315a3 |
| Adasa | 3.45 | Not recorded | 68fa6bf91e209131cea315a3 |

### MARS

Accuracy: 83.55. Result ID: 698eb126ffc3901de09fd722.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

[Implementation](<https://github.com/ChrisIsKing/black-box-multi-agent-integation>)

Recorded evaluation configuration: {"Approach Technique":"Response Selection"}. This record does not assert independent reproduction.

### USE QA

Accuracy: 71.66. Result ID: 698eb126ffc3901de09fd720.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fa1e209131cea0d9e7.md>)

Recorded evaluation configuration: {"Approach Technique":"Response Selection"}. This record does not assert independent reproduction.

### USE

Accuracy: 64.42. Result ID: 698eb126ffc3901de09fd71f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Response Selection"}. This record does not assert independent reproduction.

### Roberta

Accuracy: 61.88. Result ID: 698eb126ffc3901de09fd71a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

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

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

Recorded evaluation configuration: {"Approach Technique":"Question Agent Pairing (QA Labels)"}. This record does not assert independent reproduction.

### BM25

Accuracy: 59.94. Result ID: 698eb126ffc3901de09fd71e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Response Selection"}. This record does not assert independent reproduction.

### Bert

Accuracy: 59.1. Result ID: 698eb126ffc3901de09fd718.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

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

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

Recorded evaluation configuration: {"Approach Technique":"Question Agent Pairing (QA Labels)"}. This record does not assert independent reproduction.

### Roberta+STS

Accuracy: 56.82. Result ID: 698eb126ffc3901de09fd721.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66441e209131cea0f5ab.md>)

[Implementation](<https://github.com/UKPLab/sentence-transformers>)

Recorded evaluation configuration: {"Approach Technique":"Response Selection"}. This record does not assert independent reproduction.

### Electra

Accuracy: 52.86. Result ID: 698eb126ffc3901de09fd719.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673f1e209131cea15373.md>)

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

Recorded evaluation configuration: {"Approach Technique":"Question Agent Pairing (QA Labels)"}. This record does not assert independent reproduction.

### Google

Accuracy: 48.06. Result ID: 698eb126ffc3901de09fd724.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Individual Agents"}. This record does not assert independent reproduction.

### Alexa

Accuracy: 44.09. Result ID: 698eb126ffc3901de09fd723.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Individual Agents"}. This record does not assert independent reproduction.

### USE

Accuracy: 43.59. Result ID: 698eb126ffc3901de09fd71c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Question Agent Pairing (Descriptions)"}. This record does not assert independent reproduction.

### Roberta+STS

Accuracy: 36.67. Result ID: 698eb126ffc3901de09fd71d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66441e209131cea0f5ab.md>)

[Implementation](<https://github.com/UKPLab/sentence-transformers>)

Recorded evaluation configuration: {"Approach Technique":"Question Agent Pairing (Descriptions)"}. This record does not assert independent reproduction.

### Houndify

Accuracy: 32.04. Result ID: 698eb126ffc3901de09fd725.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Individual Agents"}. This record does not assert independent reproduction.

### BM25

Accuracy: 23.69. Result ID: 698eb126ffc3901de09fd71b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Question Agent Pairing (Descriptions)"}. This record does not assert independent reproduction.

### Adasa

Accuracy: 3.45. Result ID: 698eb126ffc3901de09fd726.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf91e209131cea315a3.md>)

Recorded evaluation configuration: {"Approach Technique":"Individual Agents"}. This record does not assert independent reproduction.

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