FSD Version Tracker
FSD VersionsFSD NewsContributorsAbout
FSD Version Tracker
FSD Update

The community-driven platform tracking every Tesla Full Self-Driving software release — versions, release notes, firmware, and real-world demo videos.

Not affiliated with Tesla, Inc.

Browse

  • FSD Versions
  • FSD News
  • Contributors

Company

  • About
  • Contact
  • FAQ

Legal

  • Privacy Policy
  • Terms of Service
  • Data Deletion

© 2026 FSD Update. All rights reserved.

Tracking Tesla FSD updates since 2021.

Tesla FSD Version Tracker - Full Self-Driving Updates and Release Notes

Tesla FSD Version Tracker

Track the latest Full Self-Driving updates, release notes, and demonstrations.

What Is Tesla Full Self-Driving (FSD)?

Tesla Full Self-Driving — currently branded as FSD Supervised— is Tesla’s most advanced driver-assistance system. Built on an end-to-end neural network that processes camera inputs to generate driving commands, FSD can navigate city streets, handle intersections, make unprotected turns, respond to traffic signals, and manage highway driving — all with minimal driver input.

Despite its name, FSD is not fully autonomous. The driver must remain attentive, keep their hands on the steering wheel, and be prepared to intervene at any moment. Tesla continues to improve FSD through frequent over-the-air software updates, each introducing refinements to the vehicle’s perception, planning, and control systems.

FSD is available as an add-on purchase or monthly subscription for compatible Tesla vehicles including Model S, Model 3, Model X, Model Y, and Cybertruck. Hardware requirements and feature availability may vary by model and region.

Why Track FSD Software Versions?

Tesla updates FSD software frequently — sometimes multiple times per month. Each update can include changes to how the vehicle perceives its environment, plans routes, handles edge cases, and responds to obstacles. For Tesla owners, keeping track of these changes matters for several reasons:

  • Understanding what changed: Release notes explain the improvements and fixes in each version, helping owners know what to expect after an update.
  • Comparing versions: By reviewing release notes and demonstration videos side by side, you can see how the software has progressed over time.
  • Confirming your software: Knowing the latest version helps you verify whether your vehicle is up to date or still waiting for an update.
  • Real-world performance: Community demonstration videos show how each version actually performs on different road types, in various conditions, and across different Tesla models.

What You’ll Find on FSD Update

Complete Version History

Every FSD release cataloged with version number, release date, firmware, and compatible Tesla models.

Official Release Notes

On-screen changelogs captured directly from Tesla vehicles and published for each version.

Real-World Demo Videos

Community-contributed YouTube videos showing FSD in action, organized by version for easy comparison.

Model Filtering

Filter versions by your Tesla model — Model S, 3, X, Y, or Cybertruck — to see what's relevant to your vehicle.

FSD News & Analysis

Original articles covering significant FSD developments, major version launches, and technology analysis.

Contributor Community

A growing network of Tesla creators whose FSD demo videos provide unfiltered insight into each release.

Learn More About FSD Update

Curious about how we collect data, who our contributors are, or how to get involved? Visit our About page or check the FAQ.

About UsFAQContributors
Models:
Sort:

FSD 14.3.8

Firmware
2026.26.6.5
Release DateAug 25, 2026

No community videos for this version yet. Be the first to share yours!

  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Improved driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • You can now see distance traveled in FSD (Supervised) without an intervention. The Self-Driving App will also show your longest intervention-free streak.
  • Parking options now display on the map when arriving at your destination
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.
  • Summer Update

    Summer Update

    Swipe up to see your new features in the 2026 Summer Update.

  • Grok Commands

    Grok Commands

    Grok can now make phone calls, play music, adjust climate, and search the Controls panel. Ask Grok about your Tesla or what was included in the latest software update. Go to Grok > Settings to enable or disable "Hey Grok" and location-based reminders. Requires Premium Connectivity or a WiFi connection.

  • Self-Driving Stats

    Self-Driving Stats

    You can now view and share Self-Driving stats from your phone. Go to Mobile App > Self-Driving. Requires Mobile App v4.59.0 or later.

  • Preferred Routes

    Preferred Routes

    Navigation now prioritizes routes that you've taken before. Location data is anonymous to Tesla and not associated with your vehicle.

  • Automatic Navigation

    Automatic Navigation

    Automatic Navigation now adapts to your routine. In addition to Home, Work, and upcoming calendar events, your vehicle can now suggest and route to the places you visit regularly, like a school drop-off on the way to work, when Destination Suggestions are enabled. Location data is anonymous to Tesla and not associated with your vehicle.

  • Caraoke with Scoring

    Caraoke with Scoring

    Caraoke now scores your singing while in Park. Earn stars and track your high scores in the My Karaoke tab. On the rear display, tap the queue button to show a QR code for passengers to scan and add songs to the queue from their phones. Requires Premium Connectivity.

  • Driving Visualization

    Driving Visualization

    Customize your Self-Driving zoom preference. Pinch the visualization or select one of the presets in Controls > Self-Driving > Visualization Camera Zoom.

  • Speed Cameras on Route

    Navigation now includes symbols along your route to show speed cameras. Requires Premium Connectivity.

  • Custom Wraps

    Custom Wraps

    Use the Mobile App to upload custom wrap designs from images on your phone and send directly to your Tesla. Go to Creations > Wrap > Upload. Requires Mobile App v4.59.0 or later. To access in car, go to App Launcher > Toybox > Paint Shop.

  • Camera Preview

    Camera Preview

    You can now open Camera Preview at any time, even if your Tesla is not in Park. Go to Controls > Service > Camera Preview and tap on any camera view to see it individually. Tap the grid button to switch back to all cameras.

  • Set Arrival Energy

    Set Arrival Energy

    Set your desired Arrival Energy for any trip from your phone. Open the location tab in the Tesla Mobile App, enter your destination, and tap Set Arrival Energy. Requires Mobile App v4.58.0 or later.

  • Apple Music

    Apple Music

    Add songs to your Apple Music queue directly from Search results and Artist pages. Tap and hold a song, or tap the three-dot menu to play next, add to queue, save to your library, or mark as a favorite. Requires an active Apple Music subscription.

  • Web Browser

    Web Browser

    You can now use your Tesla's interior camera and cabin microphone in Web Browser. Tap to grant permissions when a website requests access. Camera is only available while parked.

  • Supercharger Search

    Supercharger Search

    You can now find Superchargers by name when searching for a destination.

  • Welcome Animation

    Your Tesla now welcomes you with animations when turning on. To disable, go to Controls > Display > Welcome Animation.

  • Rear Display

    Rear Display

    Disable rear touchscreen controls from the center display by going to App Launcher > Rear > Lock Rear Display. Content selected from the center display will continue to play in the rear.

  • Security Improvements

    Security Improvements

    This update includes important security fixes and improvements.

FSD 14.1 Lite

Firmware
2026.21.6
Release DateAug 9, 2026

No community videos for this version yet. Be the first to share yours!

  • Distilled the intelligence from HW4 V14 into HW3. This allows HW3 to directly learn how to handle scenarios using HW4 V14 as a guide. This process unlocks the improvements that have been made to HW4 including Reinforcement Learning (RL) and offline models for HW3.
  • Improved both proactive and reactive responsiveness across a wide variety of categories including navigation handling, merges and forks, pedestrian interactions, traffic lights, and vehicle cut-in scenarios.
  • Improved general comfort in nominal scenarios through fewer false slowdowns, smoother steering and more consistent lane centering.
  • Introduced parking, unparking, and reversing capabilities.
  • Added Arrival Options for you to select where FSD should pull over or park: in a Parking Lot, on the Street, in a Driveway.
  • Speed Profiles are now available at all times, to further customize driving style preference.

FSD 14.3.7

Firmware
2026.21.52026.21.6
Release DateAug 1, 2026

No community videos for this version yet. Be the first to share yours!

  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Improved driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • You can now see distance traveled in FSD (Supervised) without an intervention. The Self-Driving App will also show your longest intervention-free streak.
  • Parking options now display on the map when arriving at your destination
  • Expande reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.

FSD 14.3.6

Firmware
2026.20.6.11
Release DateJul 21, 2026

No community videos for this version yet. Be the first to share yours!

  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Improved driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • You can now see distance traveled in FSD (Supervised) without an intervention. The Self-Driving App will also show your longest intervention-free streak.
  • Parking options now display on the map when arriving at your destination
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.

FSD 14.3.5

Firmware
2026.20.6.6
Release DateJul 12, 2026

No community videos for this version yet. Be the first to share yours!

  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Improved driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • You can now see distance traveled in FSD (Supervised) without an intervention. The Self-Driving App will also show your longest intervention-free streak.
  • Parking options now display on the map when arriving at your destination
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.

FSD 14.3.4

Firmware
2026.14.6.102026.14.6.11
Release DateJun 11, 2026
  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Improved driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • You can now see distance traveled in FSD (Supervised) without an intervention. The Self-Driving App will also show your longest intervention-free streak.
  • Parking options now display on the map when arriving at your destination
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.
  • Actually Smart Summon

    Actually Smart Summon

    Actually Smart Summon) and Dumb Summon are now available for Cybertruck!

FSD 14.3.3

Firmware
2026.14.6.62026.14.6.7
Release DateMay 16, 2026
  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping - driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Actually Smart Summon max speed is now increased to 8mph (13km/h).
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • You can now see distance traveled in FSD (Supervised) without an intervention. The Self- Driving App will also show your longest intervention-free streak.
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.
  • Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
  • Full Self-Driving (Supervised)

    Full Self-Driving (Supervised)

    Under your supervision, Full Self-Driving (Supervised) can drive your Tesla almost anywhere. It will start from a parked position, make lane changes, select forks to follow your navigation route, navigate around other vehicles and objects, make left and right turns and park at your destination. You and anyone you authorize must use additional caution and remain attentive. It does not make your vehicle autonomous. Do not become complacent. Full Self-Driving (Supervised) is enabled on your vehicle. To use the feature, press the Start Self-Driving button on the Ul, or press the right scroll wheel button once. You can disable Full Self-Driving (Supervised) in Self-Driving Settings.

  • Self-Driving App

    Self-Driving App

    With the new Self-Driving App, subscribe with a single tap, learn how to activate and use the feature, and view ongoing stats. To open, go to App Launcher > Self-Driving.

  • Hey Grok

    Hey Grok

    Launch Grok by saying “Hey Grok." Go to Grok > Settings to enable. You can also set location based reminders, like "remind me to pick up milk when I'm near home.” Say “goodbye” to dismiss.

  • Pet Mode

    Pet Mode

    Choose and name your pet by going to Controls > Display > Customize Pet Mode.

  • Trips

    Trips

    Trips are now in the Energy app, where you can create and manage multiple trips to track energy usage across different drives, routes, or conditions. Go to App Launcher > Energy > Trips. For quick access to the Trips Card, swipe left on the Media Card.

  • Sketchpad

    Sketchpad

    Unleash your inner artist with the enhanced Sketchpad, now supporting stickers and emojis. Save your sketches to access them in the Mobile App and share. Requires Mobile App version 4.55.6 or later.

  • Music App Queuing

    Music App Queuing

    Swipe right on tracks in Apple Music or Spotify to add them to the queue. In Apple Music, tap and hold on a track to add or remove from Favorites. In Spotify, swipe left to add or remove from Liked Songs.

  • Automatic Software Updates

    Automatic Software Updates

    Your Tesla can now automatically install downloaded software updates overnight. When enabled, updates will install while your Tesla is parked and not in use, ensuring you always have the latest features and improvements. To enable, go to Controls > Software > Automatically Install Updates.

  • Dashcam Viewer Updates

    Dashcam Viewer Updates

    Recent Dashcam footage can now extend up to 24 hours, and you can save any clip for permanent storage on your Tesla or on your phone by going to App Launcher > Dashcam Viewer. To enable viewing on your phone, go to Controls > Safety and turn on View Camera via Mobile App. Clips stay on the vehicle and are never shared to Tesla. Clips downloaded to your phone now include details such as speed, steering wheel angle, and Self-Driving state. Downloads require Premium Connectivity and Mobile App version 4.55.6 or later.

  • Weather Maps Improvements

    Weather Maps Improvements

    Weather maps now show snow and rain with improved colors that make it easier to distinguish between precipitation types. You can also view the past hour of weather data to see how conditions have been changing along your route. This feature requires Premium Connectivity. To view, tap the weather icon on the map.

  • Supercharger Pricing Filter

    Supercharger Pricing Filter

    You can now choose to route only to Superchargers with Tesla pricing. When enabled, Trip Planner will avoid locations where Tesla does not set charging prices or accept Free Supercharging credits. This setting requires connectivity with Online Routing enabled. To enable, go to Controls > Navigation > Trip Planner settings.

  • Keyboard

    Keyboard

    Your selected keyboard language will also select the language used for dictation. Tap the international keyboard button to change keyboard and dictation language, without changing voice command language. Tap the mic icon in the keyboard to dictate.

  • Security Improvements

    Security Improvements

    This update includes important security fixes and improvements.

FSD 14.3.2

Firmware
2026.2.9.82026.2.9.92026.2.9.10
Release DateApr 22, 2026
  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
  • Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.
  • Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.

FSD 14.3.1

Firmware
2026.2.9.7
Release DateApr 14, 2026
  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.
  • Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.

FSD 14.3

Firmware
2026.2.9.6
Release DateApr 7, 2026
  • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
  • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
  • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
  • Mitigated unnecessary lane biasing and minor tailgating behaviors.
  • Increased decisiveness of parking spot selection and maneuvering.
  • Improved parking location pin prediction, now shown on a map with a P icon.
  • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
  • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
  • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping — driven by training on hard RL examples sourced from the Tesla fleet.
  • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
  • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
  • Expand reasoning to all behaviors beyond destination handling.
  • Add pothole avoidance.
  • Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.

FSD 14.2.2.5

Firmware
2025.45.102026.2.92026.2.9.12026.2.9.22026.2.9.3
Release DateFeb 14, 2026
  • Upgraded the neural network vision encoder, leveraging higher resolution features to further improve scenarios like handling emergency vehicles, obstacles on the road, and human gestures.
  • Added Arrival Options for you to select where FSD should park: in a Parking Lot, on the Street, in a Driveway, in a Parking Garage, or at the Curbside.
  • Added handling to pull over or yield for emergency vehicles (e.g. police cars, fire trucks, ambulances).
  • Added navigation and routing into the vision-based neural network for real-time handling of blocked roads and detours.
  • Added additional Speed Profile to further customize driving style preference.
  • Improved handling for static and dynamic gates.
  • Improved offsetting for road debris (e.g. tires, tree branches, boxes).
  • Improve handling of several scenarios including: unprotected turns, lane changes, vehicle cut-ins, and school busses.
  • Improved FSD's ability to manage system faults and recover smoothly from degraded operation for enhanced reliability.
  • Added alerting for residue build-up on interior windshield that may impact front camera visibility. If affected, visit Service for cleaning!
  • Camera visibility can lead to increased attention monitoring sensitivity.
  • Overall smoothness and sentience.
  • Parking spot selection and parking quality.

FSD 14.2.2.4

Firmware
2025.45.92025.45.9.1
Release DateJan 23, 2026
  • Upgraded the neural network vision encoder, leveraging higher resolution features to further improve scenarios like handling emergency vehicles, obstacles on the road, and human gestures.
  • Added Arrival Options for you to select where FSD should park: in a Parking Lot, on the Street, in a Driveway, in a Parking Garage, or at the Curbside.
  • Added handling to pull over or yield for emergency vehicles (e.g. police cars, fire trucks, ambulances).
  • Added navigation and routing into the vision-based neural network for real-time handling of blocked roads and detours.
  • Added additional Speed Profile to further customize driving style preference.
  • Improved handling for static and dynamic gates.
  • Improved offsetting for road debris (e.g. tires, tree branches, boxes).
  • Improved handling of several scenarios including: unprotected turns, lane changes, vehicle cut-ins, and school buses.
  • Improved FSD's ability to manage system faults and recover smoothly from degraded operation for enhanced reliability.
  • Added alerting for residue build-up on interior windshield that may impact front camera visibility. If affected, visit Service for cleaning!
  • Camera visibility can lead to increased attention monitoring sensitivity.
  • Overall smoothness and sentience.
  • Parking spot selection and parking quality.