Skip to main content

MetaSpecialist modelLimited access

SAM 3

PopularityTop group about equally popular, 2 models

75out of 100new calculation

based on two data groups, mostly search, range 66 to 85

Summary

SAM 3 is Meta’s foundation model for promptable concept segmentation in images and videos. Text, points, boxes, masks, and image exemplars can describe objects. The model detects, segments, and tracks instances instead of generating new images.

The Hugging Face checkpoint is gated and requires consent to share contact information. The weights and official code are intended for local use.

All benchmark results

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

Show all 310 published benchmark results

Page 1 of 26

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.

CountBench accuracy (Show measurement, test conditions, and source)
Source value
93.8
Metric
percent
Unit
%
Category
object-counting
Direction
Higher is better
Source type
vendor-reported
Evaluator
SAM 3 technical paper
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Table 3 object counting.
Source SAM 3 technical paper
PixMo-Count accuracy (Show measurement, test conditions, and source)
Source value
86.2
Metric
percent
Unit
%
Category
object-counting
Direction
Higher is better
Source type
vendor-reported
Evaluator
SAM 3 technical paper
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Table 3 object counting.
Source SAM 3 technical paper
SA-37 mean IoU, one click (Show measurement, test conditions, and source)
Source value
66.1
Metric
percent
Unit
%
Category
segmentation
Direction
Higher is better
Source type
vendor-reported
Evaluator
SAM 3 technical paper
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Table 6 one-click interactive segmentation.
Source SAM 3 technical paper
SA-37 mean IoU, three clicks (Show measurement, test conditions, and source)
Source value
81.3
Metric
percent
Unit
%
Category
segmentation
Direction
Higher is better
Source type
vendor-reported
Evaluator
SAM 3 technical paper
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Table 6 three-click interactive segmentation.
Source SAM 3 technical paper
SA-37 mean IoU, five clicks (Show measurement, test conditions, and source)
Source value
85.1
Metric
percent
Unit
%
Category
segmentation
Direction
Higher is better
Source type
vendor-reported
Evaluator
SAM 3 technical paper
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Table 6 five-click interactive segmentation.
Source SAM 3 technical paper
ODinW13 bbox mAP, 0-shot transfer (Show measurement, test conditions, and source)
Source value
61
Metric
average bbox mAP, AP0
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 checkpoint; Table 2 zero-shot transfer; original benchmark labels as prompts; average bbox mAP.
Context
The paper does not report a scored sample count or confidence interval for this result.
Source Meta, SAM 3 technical paper, version 2
ODinW13 bbox mAP, 10-shot transfer (Show measurement, test conditions, and source)
Source value
71.8
Metric
average bbox mAP, AP10
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 checkpoint fine-tuned on 10 examples per benchmark class without mask loss; no prompt tuning; average bbox mAP.
Context
This is a 10-shot adapted result, not an untouched checkpoint result. The paper does not report a scored sample count or confidence interval.
Source Meta, SAM 3 technical paper, version 2
RF100VL bbox mAP, 0-shot transfer (Show measurement, test conditions, and source)
Source value
15.2
Metric
average bbox mAP, AP0
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 checkpoint; Table 2 zero-shot transfer; original benchmark labels as prompts; average bbox mAP.
Context
The paper does not report a scored sample count or confidence interval for this result.
Source Meta, SAM 3 technical paper, version 2
RF100VL bbox mAP, 10-shot transfer (Show measurement, test conditions, and source)
Source value
36.5
Metric
average bbox mAP, AP10
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 checkpoint fine-tuned on 10 examples per benchmark class without mask loss; no prompt tuning; average bbox mAP.
Context
This is a 10-shot adapted result, not an untouched checkpoint result. The paper does not report a scored sample count or confidence interval.
Source Meta, SAM 3 technical paper, version 2
SA-Co/VEval SA-V cgF1 (Show measurement, test conditions, and source)
Source value
30.3
Metric
classification-gated positive micro F1
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 video PCS; text noun-phrase prompt; SA-Co/VEval SA-V subset; Table 4.
Context
The reported NPs are prompt counts in the table heading, not the scored sample denominator. No denominator or confidence interval is provided.
Source Meta, SAM 3 technical paper, version 2
SA-Co/VEval SA-V pHOTA (Show measurement, test conditions, and source)
Source value
58
Metric
pHOTA
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 video PCS; text noun-phrase prompt; SA-Co/VEval SA-V subset; Table 4.
Context
The reported NPs are prompt counts in the table heading, not the scored sample denominator. No denominator or confidence interval is provided.
Source Meta, SAM 3 technical paper, version 2
SA-Co/VEval YT-Temporal-1B cgF1 (Show measurement, test conditions, and source)
Source value
50.8
Metric
classification-gated positive micro F1
Unit
%
Direction
Higher is better
Source type
vendor-reported
Evaluator
Meta, SAM 3 technical paper, version 2
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. SAM 3 video PCS; text noun-phrase prompt; SA-Co/VEval YT-Temporal-1B subset; Table 4.
Context
The reported NPs are prompt counts in the table heading, not the scored sample denominator. No denominator or confidence interval is provided.
Source Meta, SAM 3 technical paper, version 2

Page 1 of 26

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 21 models

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

Over time

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

SAM 3EmbeddingGemma 2 70Unlimited OCR 2 55Kumo-Tabular 45TeleOCR 38

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
Promptable concept segmentation and visual tracking
Source: Model class

Input and output

Input
Text and visual prompts such as points, boxes, masks, and exemplars
Source: Input
Output
Masks, boxes, scores, and object tracks for images and videos
Source: 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

Access
Gated Hugging Face download after agreement and approval
Source: Access
License
Other license, details in the Meta model agreement
Source: License
Shutdown
None announced
no source

Further details

Scope
Segmentation and tracking, not image generation
Source: Scope

Sources and data date

Show all 15 sources

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.

TypeEvidence and data date
Research statusResearch date October 4, 2026. 9 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published

evaluated-sam-3-weight-revision

Note

Both studies identify SAM 3 but do not publish the exact evaluated weight-file revision or digest.

Not published

per-cell-sample-count-and-confidence-interval

Note

Neither paper gives per-cell scored N or confidence intervals for the imported cells. The medical table shading denotes significance ranges only.

Not published

checkpointRevision

Original wording

The article identifies official sam3.pt weights but publishes no immutable checkpoint hash or revision.

Additional sourceMeta SAM 3 model card (retrieved October 3, 2026; October 4, 2026) · Meta SAM 3 model card · Editorial description reviewed October 3, 2026
Additional sourceSAM 3 technical paper (retrieved October 4, 2026; October 17, 2026)
Additional sourceChakrabarty and Soni, Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data, v2 (retrieved October 17, 2026)
Additional sourceDong et al., More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery, v1 (retrieved October 17, 2026)
Additional sourceShujun Lv et al., From SAM 1 to SAM 3: Benchmarking Zero-Shot Cross-Domain Medical Image Segmentation, Expert Systems (retrieved October 17, 2026)
Additional sourcePromptable Concept Segmentation from Above: Evaluating SAM 3’s Zero-Shot and One-Shot Capabilities in Remote Sensing (retrieved October 17, 2026)
Additional sourceHong et al., When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation, Table 2 (retrieved October 18, 2026)
Additional sourcePromptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing (retrieved October 20, 2026)
Additional sourceRoboflow VLM-Exam mixed-detection leaderboard (retrieved October 23, 2026)
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0