# Open-domain Dialogue Evaluation on Free run Mechanical Turk 1 (initial data collection run) Source: [Open-domain Dialogue Evaluation on Free run Mechanical Turk 1 (initial data collection run)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:32.801Z Subjective human evaluation of open-domain dialogue quality based on the initial data collection run from Mechanical Turk 1, assessing criteria such as fluency, consistency, and engagement. 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 | Open-domain Dialogue Evaluation | | Dataset (including any stated split) | Free run Mechanical Turk 1 (initial data collection run) | | Metric | Overall Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 Score](): Higher is better; unit: SCALAR. - [Interestingness Score](): Higher is better; unit: SCALAR. - [Fun Score](): Higher is better; unit: SCALAR. - [Consistency Score](): Higher is better; unit: SCALAR. - [Fluency Score](): Higher is better; unit: SCALAR. - [Topic Adherence Score](): Higher is better; unit: SCALAR. - [Robotic Score](): Lower is better; unit: SCALAR. - [Repetitiveness Score](): Lower is better; unit: SCALAR. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | Bi-Encoder Transformer | 0.534 | Not recorded | 68fa6bfd1e209131cea317ab | | Poly-Encoder Transformer | 0.419 | Not recorded | 68fa6bfd1e209131cea317ab | | Bi-Encoder Transformer | 0.318 | Not recorded | 68fa6bfd1e209131cea317ab | | Key-Value Memory Network | 0.262 | Not recorded | 68fa6bfd1e209131cea317ab | | Key-Value Memory Network | 0.189 | Not recorded | 68fa6bfd1e209131cea317ab | | Poly-Encoder Transformer | 0.173 | Not recorded | 68fa6bfd1e209131cea317ab | | Sequence to Sequence | -0.087 | Not recorded | 68fa6bfd1e209131cea317ab | | Sequence to Sequence | -0.201 | Not recorded | 68fa6bfd1e209131cea317ab | | LSTM-based Model | -0.217 | Not recorded | 68fa6bfd1e209131cea317ab | | LSTM-based Model | -0.243 | Not recorded | 68fa6bfd1e209131cea317ab | ### Bi-Encoder Transformer Overall Score: 0.534. Result ID: 698eb530ffc3901de09ff976. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"false","n":"798"}. This record does not assert independent reproduction. ### Poly-Encoder Transformer Overall Score: 0.419. Result ID: 698eb530ffc3901de09ff977. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"false","n":"798"}. This record does not assert independent reproduction. ### Bi-Encoder Transformer Overall Score: 0.318. Result ID: 698eb530ffc3901de09ff978. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"true","n":"707"}. This record does not assert independent reproduction. ### Key-Value Memory Network Overall Score: 0.262. Result ID: 698eb530ffc3901de09ff979. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"false","n":"791"}. This record does not assert independent reproduction. ### Key-Value Memory Network Overall Score: 0.189. Result ID: 698eb530ffc3901de09ff97a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"true","n":"714"}. This record does not assert independent reproduction. ### Poly-Encoder Transformer Overall Score: 0.173. Result ID: 698eb530ffc3901de09ff97b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"true","n":"707"}. This record does not assert independent reproduction. ### Sequence to Sequence Overall Score: -0.087. Result ID: 698eb530ffc3901de09ff97c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"false","n":"707"}. This record does not assert independent reproduction. ### Sequence to Sequence Overall Score: -0.201. Result ID: 698eb530ffc3901de09ff97d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":"true","n":"798"}. This record does not assert independent reproduction. ### LSTM-based Model Overall Score: -0.217. Result ID: 698eb530ffc3901de09ff97e. [Reporting paper]() Recorded evaluation configuration: {"persona":"true","n":"763"}. This record does not assert independent reproduction. ### LSTM-based Model Overall Score: -0.243. Result ID: 698eb530ffc3901de09ff97f. [Reporting paper]() Recorded evaluation configuration: {"persona":"false","n":"742"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.