AI Battle > Rankings > Conversational Dynamics (Full Duplex Bench subset)

Conversational Dynamics (Full Duplex Bench subset) Ranking — Speech-to-Speech (2026)

null by null leads the Conversational Dynamics (Full Duplex Bench subset) ranking with a score of 0.98. The ranking covers 20 evaluated speech-to-speech from a public dataset that AI Battle re-checks daily.

Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 20 entries shown.

Qwen Audio 3.0 Realtime Plus, Alibaba Cloud0.98GPT-Live-1 (Sol, low), OpenAI0.97Qwen Audio 3.0 Realtime Flash, Alibaba Cloud0.97GPT-Realtime-2 (Minimal)0.96GPT-Realtime-2.1 High, OpenAI0.96GPT Realtime Mini (Oct '25)0.96GPT-Realtime-2 (High)0.95Grok Voice Think Fast 2.0 High0.95GPT-Live-1 (Astra, medium), OpenAI0.95GPT-Realtime-2.1 Mini High, OpenAI0.92Personaplex 7B v10.91Deepslate Opal0.86Grok Voice Think Fast 1.00.78Gemini 3.1 Flash Live Preview - High0.74Qwen3 Omni 30B A3B Instruct (flash)0.73Gemini 3.1 Flash Live Preview - Minimal0.72Grok Voice Fast 1.00.72FLM-Audio0.62Moshi0.61Freeze-Omni0.59
Every entry in the dataset, scaled from the smallest to the largest published value.

All 20 entries in this dataset

#EntryCreatorValueΔ vs #1
1Qwen Audio 3.0 Realtime Plus, Alibaba Cloud0.980.0%
2GPT-Live-1 (Sol, low), OpenAI0.97-1.2%
3Qwen Audio 3.0 Realtime Flash, Alibaba Cloud0.97-1.5%
4GPT-Realtime-2 (Minimal)0.96-2.4%
5GPT-Realtime-2.1 High, OpenAI0.96-2.7%
6GPT Realtime Mini (Oct '25)0.96-2.8%
7GPT-Realtime-2 (High)0.95-3.2%
8Grok Voice Think Fast 2.0 High0.95-3.3%
9GPT-Live-1 (Astra, medium), OpenAI0.95-3.5%
10GPT-Realtime-2.1 Mini High, OpenAI0.92-6.8%
11Personaplex 7B v10.91-7.5%
12Deepslate Opal0.86-12.9%
13Grok Voice Think Fast 1.00.78-20.9%
14Gemini 3.1 Flash Live Preview - High0.74-24.5%
15Qwen3 Omni 30B A3B Instruct (flash)0.73-26.2%
16Gemini 3.1 Flash Live Preview - Minimal0.72-26.6%
17Grok Voice Fast 1.00.72-27.3%
18FLM-Audio0.62-37.0%
19Moshi0.61-38.0%
20Freeze-Omni0.59-40.3%

How the values are distributed

Across the 20 numeric entries in this window the median is 0.91 and the mean is 0.84, so the typical entry sits 0.07 below the leader. The window spans 0.59 to 0.98.

30320129
8 equal buckets between the smallest (0.59) and largest (0.98) value; numbers under bars are entry counts.

10 of 20 entries are at or above the median, and the top three hold 17% of the combined value — read it against the metric below, since a higher number is not "better" for every dataset.

Who publishes these entries

The source dataset for this family does not publish a provider or creator label per entry, so AI Battle cannot group them: the table above is the complete published list. Where the dataset does carry a label (model, gateway and tool families do), this section names the creators and how many entries each holds.

Metric reference

This ranking carries the metric fdbScore from the Conversational Dynamics (Full Duplex Bench subset) dataset in the tab::s2s family. Units and the direction of "better" are not declared by the source dataset, so AI Battle does not invent them: values are shown exactly as published, and the ordering is the source dataset's own.

How this ranking is built

Rebuilt on from the public dataset Conversational Dynamics (Full Duplex Bench subset) (family tab::s2s). The source lists 20 entries and all 20 are shown here. AI Battle requests the dataset's rows, keeps the ordering the source publishes, and computes only the statistics on this page: median, mean, spread, the #1–#2 gap, the creator breakdown and the raw-data file. Nothing on this page is generated text about the entries — the numbers come from the source.

Refresh cadence: every deploy re-pulls the dataset, so this page tracks the source's own update cycle. Corrections: see the methodology page.

Limitations

Raw data

Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/s2s-conversational-dynamics-full-duplex-bench-subset.json. Free to reuse with attribution to AI Battle and the source dataset.

FAQ — Conversational Dynamics (Full Duplex Bench subset)

What is the best model for Conversational Dynamics (Full Duplex Bench subset) in 2026?

null by null currently leads the Conversational Dynamics (Full Duplex Bench subset) ranking with a score of 0.98, the highest value in this dataset across Speech-to-Speech. AI Battle aggregates the dataset from its public source and re-checks it daily.

How often is the Conversational Dynamics (Full Duplex Bench subset) ranking updated?

The Conversational Dynamics (Full Duplex Bench subset) ranking is rebuilt daily from the upstream public dataset. Scores are the source dataset's own published values, so positions track whatever that source last released — each ranking page names the dataset it comes from.

Which models rank in the top 3 for Conversational Dynamics (Full Duplex Bench subset)?

The top 3 are: 1. null (0.98), 2. null (0.97), 3. null (0.97).

All AI Battle Rankings

Directories