# Open-domain Dialogue Evaluation on Free Run 2 1.0 (secondary data collection run) Source: [Open-domain Dialogue Evaluation on Free Run 2 1.0 (secondary data collection run)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:32.011Z Subjective human evaluation of open-domain dialogue quality using the Free Run 2 1.0 secondary data collection run, assessing dimensions like overall quality, interest, fun, consistency, fluency, topic adherence, and robotic/repetitive tendencies. 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 2 1.0 (secondary data collection run) | | Metric | Overall Quality 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 Quality Score](): Higher is better; unit: SCALAR. - [Interesting 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 Tendency Score](): Lower is better; unit: SCALAR. - [Repetitive Tendency Score](): Lower is better; unit: SCALAR. ## Recorded results | Method | Overall Quality Score | Result date | Report paper | | --- | --- | --- | --- | | Bi-Encoder Transformer | 0.455 | Not recorded | 68fa6bfd1e209131cea317ab | | Bi-Encoder Transformer | 0.423 | Not recorded | 68fa6bfd1e209131cea317ab | | Poly-Encoder Transformer | 0.344 | Not recorded | 68fa6bfd1e209131cea317ab | | Poly-Encoder Transformer | 0.26 | Not recorded | 68fa6bfd1e209131cea317ab | | Key-Value Memory Network | 0.245 | Not recorded | 68fa6bfd1e209131cea317ab | | Key-Value Memory Network | 0.154 | Not recorded | 68fa6bfd1e209131cea317ab | | Sequence to Sequence | 0.002 | Not recorded | 68fa6bfd1e209131cea317ab | | Language Model | -0.202 | Not recorded | 68fa6bfd1e209131cea317ab | | Language Model | -0.218 | Not recorded | 68fa6bfd1e209131cea317ab | | Sequence to Sequence | -0.258 | Not recorded | 68fa6bfd1e209131cea317ab | ### Bi-Encoder Transformer Overall Quality Score: 0.455. Result ID: 698eb530ffc3901de09ff962. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":false,"n (total ratings)":623}. This record does not assert independent reproduction. ### Bi-Encoder Transformer Overall Quality Score: 0.423. Result ID: 698eb530ffc3901de09ff963. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":true,"n (total ratings)":539}. This record does not assert independent reproduction. ### Poly-Encoder Transformer Overall Quality Score: 0.344. Result ID: 698eb530ffc3901de09ff964. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":false,"n (total ratings)":553}. This record does not assert independent reproduction. ### Poly-Encoder Transformer Overall Quality Score: 0.26. Result ID: 698eb530ffc3901de09ff965. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":true,"n (total ratings)":630}. This record does not assert independent reproduction. ### Key-Value Memory Network Overall Quality Score: 0.245. Result ID: 698eb530ffc3901de09ff966. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":false,"n (total ratings)":539}. This record does not assert independent reproduction. ### Key-Value Memory Network Overall Quality Score: 0.154. Result ID: 698eb530ffc3901de09ff967. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":true,"n (total ratings)":609}. This record does not assert independent reproduction. ### Sequence to Sequence Overall Quality Score: 0.002. Result ID: 698eb530ffc3901de09ff968. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":false,"n (total ratings)":595}. This record does not assert independent reproduction. ### Language Model Overall Quality Score: -0.202. Result ID: 698eb530ffc3901de09ff969. [Reporting paper]() Recorded evaluation configuration: {"persona":false,"n (total ratings)":567}. This record does not assert independent reproduction. ### Language Model Overall Quality Score: -0.218. Result ID: 698eb530ffc3901de09ff96a. [Reporting paper]() Recorded evaluation configuration: {"persona":true,"n (total ratings)":511}. This record does not assert independent reproduction. ### Sequence to Sequence Overall Quality Score: -0.258. Result ID: 698eb530ffc3901de09ff96b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"persona":true,"n (total ratings)":679}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.