Skip to main content

OpenMOSS TeamAudio modelOpen weights

MOSS-Audio-4B-Thinking

PopularityRank 18 of 24 audio models

25out of 100new calculation

usage data only, range 12 to 39

Summary

MOSS-Audio-4B-Thinking combines audio understanding with text reasoning. The roughly 4.6-billion-parameter model accepts audio and text and can answer questions, caption recordings, or produce timestamped transcripts.

The output remains text. Despite its audio input, MOSS-Audio-4B-Thinking is not a speech synthesizer and does not produce a spoken answer. The weights are available locally under Apache-2.0.

GraduallyBench Audio

MOSS-Audio-4B-Thinking

Partially tested
  • The test coverage is incomplete.
  • Only a short functional test is available.
  • The functional test does not assess content quality.
  • Only a technical test is available.
  • The selection of test inputs is limited.
  • Only the presence of an output was checked.
  • Five of the eight outputs in this MOSS test reached the token limit.
Show test details

Technical measurement

Local · German, English

8 valid outputs from 8 attempted and 8 planned test slots.

No further scored metric is available for this test.

WER compares words and CER compares characters with the reference. The speech output was re-transcribed with GPT Transcribe. Its exact backend revision is unconfirmed. Read speech and digital silence do not cover spontaneous speech or real background noise. Error rates can exceed 100 %. Where used, the test references were not independently reviewed by humans. Test coverage and methods differ by model. Each metric stands on its own; there is no combined overall score across tests. Data compiled on 11/10/2026. How we test · Download all Decision and Audio results as JSON

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 5 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

MMAU (Show measurement, test conditions, and source)
Source value
77.64
Metric
score
Unit
No unit provided
Benchmark version
source version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
MOSS-Audio model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Exact 4B-Thinking row; audio understanding table, not ASR
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source MOSS-Audio model card
MMAU-Pro (Show measurement, test conditions, and source)
Source value
60.75
Metric
score
Unit
No unit provided
Benchmark version
source version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
MOSS-Audio model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Exact 4B-Thinking row; audio understanding table, not ASR
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source MOSS-Audio model card
MMAR (Show measurement, test conditions, and source)
Source value
63.91
Metric
score
Unit
No unit provided
Benchmark version
source version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
MOSS-Audio model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Exact 4B-Thinking row; audio understanding table, not ASR
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source MOSS-Audio model card
MMSU (Show measurement, test conditions, and source)
Source value
71.2
Metric
score
Unit
No unit provided
Benchmark version
source version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
MOSS-Audio model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Exact 4B-Thinking row; audio understanding table, not ASR
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source MOSS-Audio model card
General Audio Understanding average accuracy (Show measurement, test conditions, and source)
Source value
68.37
Metric
accuracy
Unit
No unit provided
Benchmark version
source version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
MOSS-Audio model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Exact 4B-Thinking row; audio understanding table, not ASR
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source MOSS-Audio model card

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 54 models

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 20, 2026

MOSS-Audio-4B-ThinkingVoxtral Mini TTS 26Lyria 3 Clip 26Voxtral Mini Transcribe 2 26Eleven Flash v2.5 22

Method changes in the timeline, a jump at these points is no market event:

  1. 1November 1, 2026: Value only with search or usage data, 30-day attention
  2. 2November 1, 2026: Method version 4 (common scale, shrinkage)
  3. 3November 9, 2026: New topics measurement V20 (daily quorum, short forms)

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

All specifications

Architecture

Model class
Audio understanding and text reasoning
Source: Model class
Checkpoint
OpenMOSS-Team/MOSS-Audio-4B-Thinking
Source: Checkpoint

Input and output

Input
Audio and text
Source: Input
Output
Text
Source: Output
Reasoning
Generates text answers with a Qwen3-4B backbone, not spoken audio responses
Source: Reasoning

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Local weights
Source: Access
License
Apache-2.0
Source: License
Shutdown
None announced
no source

Further details

Tasks
ASR, audio question answering, audio captioning, and timestamped ASR
Source: Tasks
Repository
Official OpenMOSS Audio repository
Source: Repository

Sources and data date

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.