Can GPT-5.6 Luna write working Godot 4 code? 15 of 15 on the first try

By Eduardo Orellana · Updated

GPT-5.6 Luna passed 15 of 15 Godot 4 tasks on the first try and 15 of 15 after one fix with the test's output, each run headless on Godot 4.7.2. It missed none.

AppImage, x86_64. Ubuntu 22.04, Debian 12, Fedora 39 or newer.

Intel or AMD Chromebook, with Linux turned on.

Download for macOSDownload for Windows

Every model measured on the same Godot 4 tasks, each run headless on Godot 4.7.2 at a fixed 60 frames per second.

Measured by Flockbay: the same tasks, the same checks, one fix allowed with the test output.

Every model measured on the same Godot 4 tasks, each run headless on Godot 4.7.2 at a fixed 60 frames per second., checked 18 October 2026
ModelFirst tryAfter one fixAgentRun onRead from
Claude Opus 5.515 of 1515 of 15Claude Code2026-10-06Claude Opus 5.5 results
Claude Sonnet 5.515 of 1515 of 15Claude Code2026-10-06Claude Sonnet 5.5 results
GPT-6.1 Sol15 of 1515 of 15Codex2026-10-06GPT-6.1 Sol results
DeepSeek V4.1 Flash15 of 1515 of 15Hosted, by API2026-10-18DeepSeek V4.1 Flash results
Ember-115 of 1515 of 15Hosted, by API2026-10-18Ember-1 results
Gemini 3.1 Pro Preview15 of 1515 of 15Hosted, by API2026-10-18Gemini 3.1 Pro Preview results
Muse Wonder15 of 1515 of 15Hosted, by API2026-10-18Muse Wonder results
Kimi K315 of 1515 of 15Hosted, by API2026-10-18Kimi K3 results
GPT-5.6 Luna15 of 1515 of 15Hosted, by API2026-10-18GPT-5.6 Luna results
GPT-6 Luna15 of 1515 of 15Hosted, by API2026-10-18GPT-6 Luna results
Hy4 preview15 of 1515 of 15Hosted, by API2026-10-18Hy4 preview results
Pareto 26.1015 of 1515 of 15Hosted, by API2026-10-18Pareto 26.10 results
Claude Haiku 5.514 of 1515 of 15Hosted, by API2026-10-18Claude Haiku 5.5 results
MiMo-V2.6-Pro-UltraSpeed14 of 1515 of 15Hosted, by API2026-10-18MiMo-V2.6-Pro-UltraSpeed results
GLM 5.214 of 1515 of 15Hosted, by API2026-10-18GLM 5.2 results
DeepSeek V4 Pro 081314 of 1514 of 15Hosted, by API2026-10-18DeepSeek V4 Pro 0813 results
GPT-5.414 of 1514 of 15Hosted, by API2026-10-18GPT-5.4 results
MiniMax M313 of 1514 of 15Hosted, by API2026-10-18MiniMax M3 results
Qwen3.7 Max13 of 1514 of 15Hosted, by API2026-10-18Qwen3.7 Max results
Fugu Max13 of 1514 of 15Hosted, by API2026-10-18Fugu Max results
Beam 1.0 501B A23B12 of 1514 of 15Hosted, by API2026-10-18Beam 1.0 501B A23B results
Mistral Large 412 of 1513 of 15Hosted, by API2026-10-18Mistral Large 4 results
Claude Haiku 4.511 of 1514 of 15Claude Code2026-10-06Claude Haiku 4.5 results
Nemotron 3.5 Super VL11 of 1514 of 15Hosted, by API2026-10-18Nemotron 3.5 Super VL results
LongCat 2.011 of 1513 of 15Hosted, by API2026-10-18LongCat 2.0 results
Grok 4.311 of 1513 of 15Hosted, by API2026-10-18Grok 4.3 results
Laguna S 2.19 of 1512 of 15Hosted, by API2026-10-18Laguna S 2.1 results
Nova 2 Lite2 of 154 of 15Hosted, by API2026-10-18Nova 2 Lite results

How the test works

Each task asks for one GDScript file with a stated API, in a fresh Godot project. GPT-5.6 Luna was asked through its API, the way Flockbay reaches its hosted models: the task in one request, no tools, and the whole file back in a code block. A check scene then loaded the file and drove it on Godot 4.7.2, headless, at a fixed 60 frames per second: it pressed input actions, stepped physics, waited on timers and signals, and compared the results.

When a task failed, the model got the check's output once and could fix its file. Every task touches an API that changed between Godot 3 and Godot 4, or was added since: move_and_slide and is_on_floor, FileAccess and JSON, signals, tweens, Timer nodes, PackedScene, TileMapLayer, ray queries, AStarGrid2D, AnimationLibrary, and lambdas, which capture local variables by value.

The checks themselves are tested first: each passes on a reference answer and fails on an empty script. Run on 2026-10-18.

More on this: The best AI for Godot: we ran 28 models on 15 Godot 4 tasks

GPT-5.6 Luna in Flockbay

GPT-5.6 Luna is a hosted model in the Flockbay app's model menu, on the Hobby plan and above. It uses the plan's hosted usage about 2.1 times as fast as Auto.

It takes images, so Flockbay can show it screenshots of your game, and it has an effort setting in the composer, from quick answers to longer reasoning.

Move a CharacterBody2D with an input action: pass

The task: Write res://player.gd for Godot 4: a script for a CharacterBody2D that moves right at 200 pixels per second while the input action "ui_right" is held, and stands still otherwise.

Passed on the first try.

extends CharacterBody2D

const SPEED := 200.0

func _physics_process(_delta: float) -> void:
	if Input.is_action_pressed("ui_right"):
		velocity.x = SPEED
	else:
		velocity.x = 0.0

	velocity.y = 0.0
	move_and_slide()

Fall with gravity and land on the floor: pass

The task: Write res://ball.gd for Godot 4: a script for a CharacterBody2D that falls with a gravity of 980 pixels per second squared and stops when it lands on the floor. The scene gives it its collision shape.

Passed on the first try.

extends CharacterBody2D

const GRAVITY := 980.0

func _physics_process(delta: float) -> void:
	if not is_on_floor():
		velocity.y += GRAVITY * delta
	else:
		velocity.y = 0.0

	move_and_slide()

A score label: pass

The task: Write res://score_label.gd for Godot 4: a script for a Label that shows "Score: 0" when it enters the scene, and has a method add(points: int) that adds to the score and updates the text to "Score: <total>".

Passed on the first try.

extends Label

var score: int = 0


func _ready() -> void:
	_update_label()


func add(points: int) -> void:
	score += points
	_update_label()


func _update_label() -> void:
	text = "Score: %d" % score

Save and load a dictionary as JSON: pass

The task: Write res://save_game.gd for Godot 4: a script extending RefCounted with two static functions: save_data(data: Dictionary, path: String) -> void writes the dictionary to the file as JSON, and load_data(path: String) -> Dictionary reads it back.

Passed on the first try.

extends RefCounted


static func save_data(data: Dictionary, path: String) -> void:
	var file := FileAccess.open(path, FileAccess.WRITE)
	if file == null:
		return

	file.store_string(JSON.stringify(data))


static func load_data(path: String) -> Dictionary:
	if not FileAccess.file_exists(path):
		return {}

	var file := FileAccess.open(path, FileAccess.READ)
	if file == null:
		return {}

	var parsed: Variant = JSON.parse_string(file.get_as_text())
	if parsed is Dictionary:
		return parsed

	return {}

Health with signals: pass

The task: Write res://health.gd for Godot 4: a script extending Node with health starting at 100, a signal health_changed(old_value: int, new_value: int), a signal died, and a method take_damage(amount: int) that lowers health without going below 0, emits health_changed when health changes, and emits died once, when health reaches 0.

Passed on the first try.

extends Node

signal health_changed(old_value: int, new_value: int)
signal died

var health: int = 100
var _has_died: bool = false


func take_damage(amount: int) -> void:
	var old_health := health
	health = maxi(health - amount, 0)

	if health != old_health:
		health_changed.emit(old_health, health)

	if health == 0 and not _has_died:
		_has_died = true
		died.emit()

Fade out with a tween: pass

The task: Write res://fader.gd for Godot 4: a script extending Node2D with a method fade_out(duration: float) that fades the node's modulate alpha from 1 to 0 over duration seconds with a tween, and a signal faded emitted when the fade ends.

Passed on the first try.

extends Node2D

signal faded

func fade_out(duration: float) -> void:
	modulate.a = 1.0
	var tween := create_tween()
	tween.tween_property(self, "modulate:a", 0.0, duration)
	await tween.finished
	faded.emit()

Spawn on a timer, then stop: pass

The task: Write res://spawner.gd for Godot 4: a script extending Node that, once in the scene, adds a new child Node2D every 0.25 seconds, using a Timer, and stops after 4 children. It keeps the number spawned in a variable spawned_count.

Passed on the first try.

extends Node

var spawned_count: int = 0
var timer: Timer


func _ready() -> void:
	timer = Timer.new()
	timer.wait_time = 0.25
	timer.one_shot = false
	timer.timeout.connect(_on_timer_timeout)
	add_child(timer)
	timer.start()


func _on_timer_timeout() -> void:
	if spawned_count >= 4:
		timer.stop()
		return

	var child := Node2D.new()
	child.name = "SpawnedNode%d" % (spawned_count + 1)
	add_child(child)
	spawned_count += 1

	if spawned_count >= 4:
		timer.stop()

A door with states: pass

The task: Write res://door.gd for Godot 4: a script extending Node for a door with the states CLOSED, OPENING and OPEN. It starts CLOSED. A method interact() starts opening a closed door; 0.5 seconds of game time later it is OPEN. A method get_state_name() -> String returns "CLOSED", "OPENING" or "OPEN".

Passed on the first try.

extends Node

enum DoorState {
	CLOSED,
	OPENING,
	OPEN
}

const OPENING_DURATION := 0.5

var state: int = DoorState.CLOSED
var opening_time_remaining := 0.0


func interact() -> void:
	if state == DoorState.CLOSED:
		state = DoorState.OPENING
		opening_time_remaining = OPENING_DURATION


func _process(delta: float) -> void:
	if state == DoorState.OPENING:
		opening_time_remaining -= delta
		if opening_time_remaining <= 0.0:
			opening_time_remaining = 0.0
			state = DoorState.OPEN


func get_state_name() -> String:
	match state:
		DoorState.CLOSED:
			return "CLOSED"
		DoorState.OPENING:
			return "OPENING"
		DoorState.OPEN:
			return "OPEN"
		_:
			return "CLOSED"

An inventory with counts: pass

The task: Write res://inventory.gd for Godot 4: a script extending RefCounted with add_item(item_name: String, count: int), remove_item(item_name: String, count: int) -> bool that removes only when there are enough and returns whether it did, and get_count(item_name: String) -> int that is 0 for an item never added.

Passed on the first try.

extends RefCounted

var _items: Dictionary = {}


func add_item(item_name: String, count: int) -> void:
	_items[item_name] = get_count(item_name) + count


func remove_item(item_name: String, count: int) -> bool:
	if get_count(item_name) < count:
		return false

	_items[item_name] = get_count(item_name) - count
	return true


func get_count(item_name: String) -> int:
	return _items.get(item_name, 0)

Load a level scene from a path: pass

The task: Write res://level_loader.gd for Godot 4: a script extending Node with a method load_level(path: String) -> Node that loads the scene file at path, creates an instance of it, adds it as a child, and returns it.

Passed on the first try.

extends Node


func load_level(path: String) -> Node:
	var scene := load(path) as PackedScene
	if scene == null:
		push_error("Failed to load level scene: " + path)
		return null

	var level := scene.instantiate()
	add_child(level)
	return level

Paint cells on a TileMapLayer: pass

The task: Write res://grid_painter.gd for Godot 4.7: a script extending TileMapLayer with paint_row(y: int, from_x: int, to_x: int) that sets the cells from (from_x, y) to (to_x, y) inclusive to tile source 0, atlas coordinates (0, 0), and is_painted(cell: Vector2i) -> bool that says whether a cell has a tile.

Passed on the first try.

extends TileMapLayer


func paint_row(y: int, from_x: int, to_x: int) -> void:
	for x in range(from_x, to_x + 1):
		set_cell(Vector2i(x, y), 0, Vector2i(0, 0))


func is_painted(cell: Vector2i) -> bool:
	return get_cell_source_id(cell) != -1

Cast a physics ray: pass

The task: Write res://line_of_sight.gd for Godot 4: a script extending Node2D with first_hit(from: Vector2, to: Vector2) -> Vector2 that casts a physics ray through the 2D world from `from` to `to` and returns the point where it first hits a collider, or `to` when it hits nothing. It is called from physics processing.

Passed on the first try.

extends Node2D


func first_hit(from: Vector2, to: Vector2) -> Vector2:
	var query := PhysicsRayQueryParameters2D.create(from, to)
	var result := get_world_2d().direct_space_state.intersect_ray(query)

	if result.is_empty():
		return to

	return result["position"]

A path on a grid around walls: pass

The task: Write res://path_finder.gd for Godot 4: a script extending RefCounted with find_path(size: Vector2i, walls: Array[Vector2i], from: Vector2i, to: Vector2i) -> Array[Vector2i] that returns the shortest path of grid cells from `from` to `to`, both included, on a grid of `size` cells, never entering a wall cell and moving only up, down, left or right.

Passed on the first try.

extends RefCounted


func find_path(
	size: Vector2i,
	walls: Array[Vector2i],
	from: Vector2i,
	to: Vector2i
) -> Array[Vector2i]:
	if size.x <= 0 or size.y <= 0:
		return []

	if from.x < 0 or from.x >= size.x or from.y < 0 or from.y >= size.y:
		return []

	if to.x < 0 or to.x >= size.x or to.y < 0 or to.y >= size.y:
		return []

	var wall_set: Dictionary = {}
	for wall in walls:
		wall_set[wall] = true

	if wall_set.has(from) or wall_set.has(to):
		return []

	if from == to:
		return [from]

	var directions: Array[Vector2i] = [
		Vector2i.UP,
		Vector2i.DOWN,
		Vector2i.LEFT,
		Vector2i.RIGHT
	]

	var queue: Array[Vector2i] = [from]
	var queue_index := 0
	var visited: Dictionary = {from: true}
	var came_from: Dictionary = {}

	while queue_index < queue.size():
		var current: Vector2i = queue[queue_index]
		queue_index += 1

		for direction in directions:
			var next := current + direction

			if next.x < 0 or next.x >= size.x or next.y < 0 or next.y >= size.y:
				continue

			if wall_set.has(next) or visited.has(next):
				continue

			visited[next] = true
			came_from[next] = current

			if next == to:
				var path: Array[Vector2i] = [to]
				var step: Vector2i = to

				while step != from:
					step = came_from[step]
					path.push_front(step)

				return path

			queue.append(next)

	return []

Build and play an animation in code: pass

The task: Write res://blinker.gd for Godot 4: a script extending Node2D that, when it enters the scene, creates an AnimationPlayer child and a looping animation named "blink", 1 second long, that keeps the node visible for the first half of each second and hidden for the second half, and plays it.

Passed on the first try.

extends Node2D


func _ready() -> void:
	var animation_player := AnimationPlayer.new()
	add_child(animation_player)

	var animation := Animation.new()
	animation.length = 1.0
	animation.loop_mode = Animation.LOOP_LINEAR

	var visibility_track := animation.add_track(Animation.TYPE_VALUE)
	animation.track_set_path(visibility_track, NodePath(".:visible"))
	animation.track_set_interpolation_type(visibility_track, Animation.INTERPOLATION_NEAREST)
	animation.track_insert_key(visibility_track, 0.0, true)
	animation.track_insert_key(visibility_track, 0.5, false)
	animation.track_insert_key(visibility_track, 1.0, true)

	var library := AnimationLibrary.new()
	library.add_animation("blink", animation)
	animation_player.add_animation_library("", library)

	animation_player.play("blink")

Wait for a signal or a timeout: pass

The task: Write res://waiter.gd for Godot 4: a script extending Node with wait_for(sig: Signal, seconds: float) -> bool, a coroutine that waits until the signal is emitted or `seconds` of game time pass, whichever comes first, and returns true if the signal came first. The signal has no arguments.

Passed on the first try.

extends Node


class _WaitState extends RefCounted:
	signal finished

	var result: bool = false
	var _completed: bool = false
	var _source: Signal
	var _timer: SceneTreeTimer

	func _init(source: Signal, tree: SceneTree, seconds: float) -> void:
		_source = source
		_timer = tree.create_timer(maxf(seconds, 0.0))
		_source.connect(_on_source)
		_timer.timeout.connect(_on_timeout)

	func _on_source() -> void:
		_complete(true)

	func _on_timeout() -> void:
		_complete(false)

	func _complete(value: bool) -> void:
		if _completed:
			return

		_completed = true
		result = value

		if _source.is_connected(_on_source):
			_source.disconnect(_on_source)
		if _timer.timeout.is_connected(_on_timeout):
			_timer.timeout.disconnect(_on_timeout)

		finished.emit()


func wait_for(sig: Signal, seconds: float) -> bool:
	var state := _WaitState.new(sig, get_tree(), seconds)
	await state.finished
	return state.result

Questions

Is GPT-5.6 Luna good at Godot?
On these 15 tasks it passed 15 on the first try and 15 after one fix. Each task is small and checked by running it, so the score says whether its Godot 4 code works, not how well it designs a game.