AI Battle > Rankings > Arena Preference Elo
null by null leads the Arena Preference Elo ranking with a score of 1096. 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.
| # | Entry | Creator | Value | Δ vs #1 |
|---|---|---|---|---|
| 1 | Gemini 3.1 Flash Live Minimal | 1096 | 0.0% | |
| 2 | Gemini 3.1 Flash Live High | 1063 | -3.0% | |
| 3 | GPT-Live-1 (Sol, low) | 1053 | -3.9% | |
| 4 | GPT-Live-1 (Astra, medium) | 1048 | -4.4% | |
| 5 | Cartesia Line (Default Cascaded System) | 1027 | -6.3% | |
| 6 | Grok Voice Think Fast 2.0 High | 1011 | -7.8% | |
| 7 | GPT-Realtime-1.5 | 1000 | -8.7% | |
| 8 | ElevenLabs Agents (Default Cascaded System) | 993 | -9.3% | |
| 9 | GPT Realtime (Aug '25) | 974 | -11.1% | |
| 10 | Nova 2.0 Sonic (Mar 2026) | 974 | -11.1% | |
| 11 | GPT-Realtime-2.1 Minimal | 937 | -14.5% | |
| 12 | GPT-Realtime-2 (High) | 932 | -15.0% | |
| 13 | GPT-Realtime-2.1 High | 928 | -15.3% | |
| 14 | GPT Realtime Mini (Oct '25) | 917 | -16.3% | |
| 15 | GPT-Realtime-2 (Minimal) | 916 | -16.4% | |
| 16 | Deepgram Voice Agent (Default Cascaded System) | 914 | -16.6% | |
| 17 | Nova Sonic | 913 | -16.7% | |
| 18 | Grok Voice Think Fast 1.0 | 908 | -17.1% | |
| 19 | Inworld Realtime (Default Cascaded System) | 867 | -20.9% | |
| 20 | Qwen3.5 Omni Plus Realtime | 859 | -21.6% |
Across the 20 numeric entries in this window the median is 956 and the mean is 967, so the typical entry sits 140 below the leader. The window spans 859 to 1096.
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.
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.
This ranking carries the metrics
elo_lower, elo_mid, elo_upper from the
Arena Preference Elo 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.
Rebuilt on from the
public dataset Arena Preference Elo (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.
Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/s2s-arena-preference-elo.json. Free to reuse with attribution to AI Battle and the source dataset.
null by null currently leads the Arena Preference Elo ranking with a score of 1096, the highest value in this dataset across Speech-to-Speech. AI Battle aggregates the dataset from its public source and re-checks it daily.
The Arena Preference Elo 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.
The top 3 are: 1. null (1096), 2. null (1063), 3. null (1053).