AI Battle > Rankings > Speech Reasoning (Big Bench Audio)

Speech Reasoning (Big Bench Audio) Ranking — Speech-to-Speech (2026)

null by null leads the Speech Reasoning (Big Bench Audio) ranking with a score of 0.99. 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 Cloud0.99Qwen3.5 Omni Plus Realtime0.99Step-Audio R1.1 (Realtime)0.98Grok Voice Think Fast 2.0 High0.97Grok Voice Think Fast 1.00.97Gemini 3.1 Flash Live Preview - High0.97GPT-Realtime-2 (High)0.97Qwen Audio 3.0 Realtime Flash, Alibaba Cloud0.96GPT-Realtime-2.1 High, OpenAI0.96Grok Voice Fast 1.00.93Gemini 2.5 Flash Native Audio Dialog Thinkin0.91GPT-Live-1 (Astra, medium), OpenAI0.90GPT-Live-1 (Sol, low), OpenAI0.89Nova 2.0 Sonic (Mar 2026)0.88Deepslate Opal0.85GPT-Realtime-2.1 Mini High, OpenAI0.75GPT-Realtime-2 (Minimal)0.72Gemini 3.1 Flash Live Preview - Minimal0.71Gemini 2.5 Flash Native Audio Dialog0.69GPT Realtime Mini (Oct '25)0.64
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 Cloud0.990.0%
2Qwen3.5 Omni Plus Realtime0.99-0.5%
3Step-Audio R1.1 (Realtime)0.98-1.6%
4Grok Voice Think Fast 2.0 High0.97-2.0%
5Grok Voice Think Fast 1.00.97-2.1%
6Gemini 3.1 Flash Live Preview - High0.97-2.6%
7GPT-Realtime-2 (High)0.97-2.6%
8Qwen Audio 3.0 Realtime Flash, Alibaba Cloud0.96-3.1%
9GPT-Realtime-2.1 High, OpenAI0.96-3.4%
10Grok Voice Fast 1.00.93-5.9%
11Gemini 2.5 Flash Native Audio Dialog Thinking0.91-8.6%
12GPT-Live-1 (Astra, medium), OpenAI0.90-9.2%
13GPT-Live-1 (Sol, low), OpenAI0.89-10.3%
14Nova 2.0 Sonic (Mar 2026)0.88-11.2%
15Deepslate Opal0.85-14.3%
16GPT-Realtime-2.1 Mini High, OpenAI0.75-24.7%
17GPT-Realtime-2 (Minimal)0.72-27.6%
18Gemini 3.1 Flash Live Preview - Minimal0.71-28.1%
19Gemini 2.5 Flash Native Audio Dialog0.69-30.8%
20GPT Realtime Mini (Oct '25)0.64-35.9%

How the values are distributed

Across the 20 numeric entries in this window the median is 0.92 and the mean is 0.88, so the typical entry sits 0.07 below the leader. The window spans 0.64 to 0.99.

13101329
8 equal buckets between the smallest (0.64) and largest (0.99) 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 bbaScore from the Speech Reasoning (Big Bench Audio) 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 Speech Reasoning (Big Bench Audio) (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-speech-reasoning-big-bench-audio.json. Free to reuse with attribution to AI Battle and the source dataset.

FAQ — Speech Reasoning (Big Bench Audio)

What is the best model for Speech Reasoning (Big Bench Audio) in 2026?

null by null currently leads the Speech Reasoning (Big Bench Audio) ranking with a score of 0.99, 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 Speech Reasoning (Big Bench Audio) ranking updated?

The Speech Reasoning (Big Bench Audio) 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 Speech Reasoning (Big Bench Audio)?

The top 3 are: 1. null (0.99), 2. null (0.99), 3. null (0.98).

All AI Battle Rankings

Directories