# Dialogue voice design on 40 multi-turn dialogues Source: [Dialogue voice design on 40 multi-turn dialogues]() Collection index: [llms.txt]() Data updated: 2026-04-10T09:32:12.688Z Evaluation of dialogue voice design performance using the 40 multi-turn dialogues dataset, measured by SIM, Context Coherence, and MOS. 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 | Dialogue voice design | | Dataset (including any stated split) | 40 multi-turn dialogues | | Metric | SIM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 2 of 2 | | 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 - [SIM](): Higher is better; unit: PERCENT. - [Context Coherence](): Higher is better; unit: SCALAR. - [MOS](): Higher is better; unit: SCALAR. ## Recorded results | Method | SIM | Result date | Report paper | | --- | --- | --- | --- | | CapTalk | 80.8 | Not recorded | 69d8843a7d0172140ec77c00 | | Fish Speech S2 Pro | 80.6 | Not recorded | 69d8843a7d0172140ec77c00 | ### CapTalk SIM: 80.8. Result ID: 69d8c39347f34ce924c1ff82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Fish Speech S2 Pro SIM: 80.6. Result ID: 69d8c39347f34ce924c1ff81. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.