PerceptronSpecialist modelActive

Perceptron Mk1.5

PopularityRank 670 of 875

0out of 100same as last month

Summary

Perceptron Mk1.5 is a multimodal model for embodied agents. It accepts text, images, video, and audio, then emits text, points, boxes, polygons, clips, and time-based object tracks. Perceptron names drones, robot dogs, smart glasses, and smartphones as deployment environments.

Access is provided through the Perceptron Platform and SDK under the API model ID perceptron-mk1.5. Perceptron specifies 32K tokens of multimodal context. The model understands audio inputs and supports tool calls. API pricing is $0.15 per 1M input tokens and $1.50 per 1M output tokens.

All benchmark results

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

Show all 33 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.

DailyOmni accuracy (Show measurement, test conditions, and source)

Source value: 74.67
Score: 74.67
Metric: percent
Unit: %
Category: audio-visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Figure 4 audio-visual evaluation.

Source Perceptron

WorldSense accuracy (Show measurement, test conditions, and source)

Source value: 50.32
Score: 50.32
Metric: percent
Unit: %
Category: audio-visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Figure 4 audio-visual evaluation.

Source Perceptron

OmniBench accuracy (Show measurement, test conditions, and source)

Source value: 51.05
Score: 51.05
Metric: percent
Unit: %
Category: audio-visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Figure 4 audio-visual evaluation.

Source Perceptron

AVHBench accuracy (Show measurement, test conditions, and source)

Source value: 80.56
Score: 80.56
Metric: percent
Unit: %
Category: audio-visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Figure 4 audio-visual evaluation.

Source Perceptron

LiveVQA-W accuracy (Show measurement, test conditions, and source)

Source value: 56
Score: 56
Metric: percent
Unit: %
Category: audio-visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Figure 5; four samples, majority vote, and tools; mean of two benchmark levels.

Source Perceptron

EgoSchema hard accuracy, Figure 3 (Show measurement, test conditions, and source)

Source value: 63.75
Score: 63.75
Metric: percent
Unit: %
Category: egocentric-video
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: disputed
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Figure 3 egocentric evaluation.
Context: The same page's final video table reports 61.3 for EgoSchema hard. Both observations are retained because their scope is unresolved.

Source Perceptron

EgoSchema hard accuracy, final table (Show measurement, test conditions, and source)

Source value: 61.3
Score: 61.3
Metric: percent
Unit: %
Category: egocentric-video
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron
Status: disputed
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Final video benchmark table.
Context: The same page's Figure 3 reports 63.75 for EgoSchema hard. Both observations are retained because their scope is unresolved.

Source Perceptron

NExT-QA hard subset accuracy (Show measurement, test conditions, and source)

Source value: 64.2
Score: 64.2
Metric: Accuracy, percent
Unit: %
Category: video-understanding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron, Introducing Perceptron Mk1.5
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Perceptron Mk1.5 (provider API model ID perceptron-mk1.5), direct provider row in the published video-understanding table. NExT-QA hard subset; the provider reports accuracy in percent, higher is better, and rounds Mk1.5 scores to one decimal. Prompt, decoding, split/version, denominator, and immutable evaluated checkpoint revision are not published.
Context: Vendor-reported score. The provider does not publish a per-row denominator, dataset split/version, prompt/decoding settings, evaluated checkpoint digest, or error/CI. The same page's EgoSchema hard figure and final table disagree; that disputed EgoSchema value is not duplicated or resolved here.

Source Perceptron, Introducing Perceptron Mk1.5

VSI-Bench hard subset accuracy (Show measurement, test conditions, and source)

Source value: 85.4
Score: 85.4
Metric: Accuracy, percent
Unit: %
Category: video-understanding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron, Introducing Perceptron Mk1.5
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Perceptron Mk1.5 (provider API model ID perceptron-mk1.5), direct provider row in the published video-understanding table. VSI-Bench hard subset; the provider reports accuracy in percent, higher is better, and rounds Mk1.5 scores to one decimal. Prompt, decoding, split/version, denominator, and immutable evaluated checkpoint revision are not published.
Context: Vendor-reported score. The provider does not publish a per-row denominator, dataset split/version, prompt/decoding settings, evaluated checkpoint digest, or error/CI. The same page's EgoSchema hard figure and final table disagree; that disputed EgoSchema value is not duplicated or resolved here.

Source Perceptron, Introducing Perceptron Mk1.5

Perception Test standard subset accuracy (Show measurement, test conditions, and source)

Source value: 67.6
Score: 67.6
Metric: Accuracy, percent
Unit: %
Category: video-understanding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron, Introducing Perceptron Mk1.5
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Perceptron Mk1.5 (provider API model ID perceptron-mk1.5), direct provider row in the published video-understanding table. Perception Test standard subset; the provider reports accuracy in percent, higher is better, and rounds Mk1.5 scores to one decimal. Prompt, decoding, split/version, denominator, and immutable evaluated checkpoint revision are not published.
Context: Vendor-reported score. The provider does not publish a per-row denominator, dataset split/version, prompt/decoding settings, evaluated checkpoint digest, or error/CI. The same page's EgoSchema hard figure and final table disagree; that disputed EgoSchema value is not duplicated or resolved here.

Source Perceptron, Introducing Perceptron Mk1.5

MVBench standard subset accuracy (Show measurement, test conditions, and source)

Source value: 73.4
Score: 73.4
Metric: Accuracy, percent
Unit: %
Category: video-understanding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron, Introducing Perceptron Mk1.5
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Perceptron Mk1.5 (provider API model ID perceptron-mk1.5), direct provider row in the published video-understanding table. MVBench standard subset; the provider reports accuracy in percent, higher is better, and rounds Mk1.5 scores to one decimal. Prompt, decoding, split/version, denominator, and immutable evaluated checkpoint revision are not published.
Context: Vendor-reported score. The provider does not publish a per-row denominator, dataset split/version, prompt/decoding settings, evaluated checkpoint digest, or error/CI. The same page's EgoSchema hard figure and final table disagree; that disputed EgoSchema value is not duplicated or resolved here.

Source Perceptron, Introducing Perceptron Mk1.5

NExT-QA standard subset accuracy (Show measurement, test conditions, and source)

Source value: 85.6
Score: 85.6
Metric: Accuracy, percent
Unit: %
Category: video-understanding
Direction: Higher is better
Source type: vendor-reported
Evaluator: Perceptron, Introducing Perceptron Mk1.5
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Perceptron Mk1.5 (provider API model ID perceptron-mk1.5), direct provider row in the published video-understanding table. NExT-QA standard subset; the provider reports accuracy in percent, higher is better, and rounds Mk1.5 scores to one decimal. Prompt, decoding, split/version, denominator, and immutable evaluated checkpoint revision are not published.
Context: Vendor-reported score. The provider does not publish a per-row denominator, dataset split/version, prompt/decoding settings, evaluated checkpoint digest, or error/CI. The same page's EgoSchema hard figure and final table disagree; that disputed EgoSchema value is not duplicated or resolved here.

Source Perceptron, Introducing Perceptron Mk1.5

Page 1 of 3

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 29 models

SAM 368

TeleOCR48

pplx-embed-v2-context-9b-preview35

Agora-233

LFM2.5-VL-3B-DSpark32

Cohere Embed v5 Fast0

Cohere Embed v5 Pro0

Cohere Rerank 5 Fast0

Perceptron Mk1.50

pplx-embed-v2-context-9b-preview

Perceptron Mk1.5

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

Over time

Weekly values from October 18, 2026 to November 5, 2026

Perceptron Mk1.5Cohere Embed v5 FastCohere Embed v5 ProCohere Rerank 5 FastCohere Rerank 5 Pro

All specifications

Architecture

Model class: Multimodal control model for embodied agents; Source: Model class

Input and output

Modalities: Text, images, video, and audio as input; Source: Modalities
Context window: 32K tokens of multimodal context (provider specification); Source: Context window

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

API

API model ID: perceptron-mk1.5; Source: API model ID

Further details

Outputs: Text, points, boxes, polygons, clips, and object tracks; Source: Outputs

Prices

Input price: $0.15 per 1M input tokensSource
Output price: $1.50 per 1M output tokensSource

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.
Unresolved	egoschema-hard-configuration Original wording The provider page gives 63.75 in Figure 3 and 61.3 in its final video table. Both are preserved and neither is selected as the canonical value.
Not published	Immutable served checkpoint and per-benchmark prompts/settings Note The official page names API model ID perceptron-mk1.5 but does not publish an immutable served-weight revision or complete prompts/settings for the evaluated figures.
Additional source	Perceptron Mk1.5 announcement (retrieved October 3, 2026; October 4, 2026; October 17, 2026; October 23, 2026; October 28, 2026) · Perceptron Mk1.5 announcement · Editorial description reviewed October 3, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0