InceptionLanguage modelEnterprise access
Mercury Voice
Mercury Voice has no overall index value yet because there are too few independent benchmark results.
n/ano search or usage data
Summary
Mercury Voice targets the time to first answer token in voice agents. In its own tests on customer-service prompts, Inception reports a median of 320 milliseconds after reasoning. Despite its name, this diffusion LLM generates text; other components handle speech recognition and audio output.
Inception offers the checkpoint through its own API for enterprise customers. It handles 128K context tokens and up to 50K output tokens.
On this page
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 20 published benchmark results
Page 1 of 2
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.
average quality (Show measurement, test conditions, and source)
- Source value
- 70.5
- Metric
- average quality reported score
- Unit
- No unit provided
- Category
- source-specific
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inceptionlabs.ai
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
- Context
- Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
tau3 Telecom (Show measurement, test conditions, and source)
- Source value
- 77.2
- Metric
- tau3 Telecom reported score
- Unit
- No unit provided
- Category
- source-specific
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inceptionlabs.ai
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
- Context
- Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
tau3 Airline (Show measurement, test conditions, and source)
- Source value
- 78
- Metric
- tau3 Airline reported score
- Unit
- No unit provided
- Category
- source-specific
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inceptionlabs.ai
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
- Context
- Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
tau3 Retail (Show measurement, test conditions, and source)
- Source value
- 69.3
- Metric
- tau3 Retail reported score
- Unit
- No unit provided
- Category
- source-specific
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inceptionlabs.ai
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
- Context
- Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
IFBench (Show measurement, test conditions, and source)
- Source value
- 67.4
- Metric
- IFBench reported score
- Unit
- No unit provided
- Category
- source-specific
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inceptionlabs.ai
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
- Context
- Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
BFCL v4 multi-turn (Show measurement, test conditions, and source)
- Source value
- 60.5
- Metric
- BFCL v4 multi-turn reported score
- Unit
- No unit provided
- Category
- source-specific
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- inceptionlabs.ai
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
- Context
- Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Average quality (MEDIUM) (Show measurement, test conditions, and source)
- Source value
- 69
- Metric
- reported chart score
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Inception Labs, Introducing Mercury Voice
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact MEDIUM column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
- Context
- The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Average quality (HIGH) (Show measurement, test conditions, and source)
- Source value
- 69.9
- Metric
- reported chart score
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Inception Labs, Introducing Mercury Voice
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact HIGH column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
- Context
- The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
τ³-bench Telecom (MEDIUM) (Show measurement, test conditions, and source)
- Source value
- 74.6
- Metric
- reported chart score
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Inception Labs, Introducing Mercury Voice
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact MEDIUM column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
- Context
- The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
τ³-bench Telecom (HIGH) (Show measurement, test conditions, and source)
- Source value
- 79.82
- Metric
- reported chart score
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Inception Labs, Introducing Mercury Voice
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact HIGH column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
- Context
- The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
τ³-bench Airline (MEDIUM) (Show measurement, test conditions, and source)
- Source value
- 78
- Metric
- reported chart score
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Inception Labs, Introducing Mercury Voice
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact MEDIUM column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
- Context
- The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
τ³-bench Airline (HIGH) (Show measurement, test conditions, and source)
- Source value
- 76
- Metric
- reported chart score
- Unit
- No unit provided
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Inception Labs, Introducing Mercury Voice
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact HIGH column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
- Context
- The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Page 1 of 2
Similar models
More models of the same kind as Mercury Voice, chosen by model line, developer, size, price and release date.
- Mercury 3Inception · same developer
- Mercury 2.5Inception · same developer
- Claude Opus 5.5Anthropic · released around the same time
- GPT-6.1 SolOpenAI · released around the same time
- GPT-6 LunaOpenAI · released around the same time
- Claude Haiku 5.5Anthropic · released around the same time
- GPT-6.1 TerraOpenAI · released around the same time
- Claude Sonnet 5.5Anthropic · released around the same time
All specifications
Architecture
Input and output
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
- Shutdown
- None announced
- no source
Frequently asked questions about Mercury Voice
Can I run Mercury Voice locally?
No. Inception does not publish the weights.
Stated by Inception
- Open weights
- no
- License
- n/a
- Parameters
- n/a
- active per token
- n/a
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.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | chart score unit Note The source chart labels the column Score but does not define the score scale. |
| Unresolved | meaning of Medium/High labels Note The exact chart labels are retained without assuming that they denote reasoning effort. |
| Not published | sample count and confidence interval Note No task denominator or 95% interval is published. |
| Additional source | Inception Mercury Voice announcement (retrieved October 3, 2026; October 4, 2026; October 17, 2026) · Inception Mercury Voice announcement · Editorial description reviewed October 4, 2026 |
| Additional source | Inception model blog (retrieved October 3, 2026) · Inception model blog · Editorial description reviewed October 4, 2026 |