Can Kimi K3 write working Godot 4 code? 15 of 15 on the first try
By Eduardo Orellana · Updated
Kimi K3 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.
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.
| Model | First try | After one fix | Agent | Run on | Read from |
|---|---|---|---|---|---|
| Claude Opus 5.5 | 15 of 15 | 15 of 15 | Claude Code | 2026-10-06 | Claude Opus 5.5 results |
| Claude Sonnet 5.5 | 15 of 15 | 15 of 15 | Claude Code | 2026-10-06 | Claude Sonnet 5.5 results |
| GPT-6.1 Sol | 15 of 15 | 15 of 15 | Codex | 2026-10-06 | GPT-6.1 Sol results |
| DeepSeek V4.1 Flash | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | DeepSeek V4.1 Flash results |
| Ember-1 | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Ember-1 results |
| Gemini 3.1 Pro Preview | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Gemini 3.1 Pro Preview results |
| Muse Wonder | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Muse Wonder results |
| Kimi K3 | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Kimi K3 results |
| GPT-5.6 Luna | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | GPT-5.6 Luna results |
| GPT-6 Luna | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | GPT-6 Luna results |
| Hy4 preview | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Hy4 preview results |
| Pareto 26.10 | 15 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Pareto 26.10 results |
| Claude Haiku 5.5 | 14 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | Claude Haiku 5.5 results |
| MiMo-V2.6-Pro-UltraSpeed | 14 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | MiMo-V2.6-Pro-UltraSpeed results |
| GLM 5.2 | 14 of 15 | 15 of 15 | Hosted, by API | 2026-10-18 | GLM 5.2 results |
| DeepSeek V4 Pro 0813 | 14 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | DeepSeek V4 Pro 0813 results |
| GPT-5.4 | 14 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | GPT-5.4 results |
| MiniMax M3 | 13 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | MiniMax M3 results |
| Qwen3.7 Max | 13 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | Qwen3.7 Max results |
| Fugu Max | 13 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | Fugu Max results |
| Beam 1.0 501B A23B | 12 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | Beam 1.0 501B A23B results |
| Mistral Large 4 | 12 of 15 | 13 of 15 | Hosted, by API | 2026-10-18 | Mistral Large 4 results |
| Claude Haiku 4.5 | 11 of 15 | 14 of 15 | Claude Code | 2026-10-06 | Claude Haiku 4.5 results |
| Nemotron 3.5 Super VL | 11 of 15 | 14 of 15 | Hosted, by API | 2026-10-18 | Nemotron 3.5 Super VL results |
| LongCat 2.0 | 11 of 15 | 13 of 15 | Hosted, by API | 2026-10-18 | LongCat 2.0 results |
| Grok 4.3 | 11 of 15 | 13 of 15 | Hosted, by API | 2026-10-18 | Grok 4.3 results |
| Laguna S 2.1 | 9 of 15 | 12 of 15 | Hosted, by API | 2026-10-18 | Laguna S 2.1 results |
| Nova 2 Lite | 2 of 15 | 4 of 15 | Hosted, by API | 2026-10-18 | Nova 2 Lite results |
How the test works
Each task asks for one GDScript file with a stated API, in a fresh Godot project. Kimi K3 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.
Kimi K3 in Flockbay
Kimi K3 is a hosted model in the Flockbay app's model menu, on the Indie Developer plan and above. It uses the plan's hosted usage about 17 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
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:
text = "Score: 0"
func add(points: int) -> void:
score += points
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:
push_error("SaveGame: could not open '%s' for writing (error %d)." % [path, FileAccess.get_open_error()])
return
file.store_string(JSON.stringify(data))
file.close()
static func load_data(path: String) -> Dictionary:
if not FileAccess.file_exists(path):
push_warning("SaveGame: file '%s' does not exist." % path)
return {}
var file := FileAccess.open(path, FileAccess.READ)
if file == null:
push_error("SaveGame: could not open '%s' for reading (error %d)." % [path, FileAccess.get_open_error()])
return {}
var text := file.get_as_text()
file.close()
var parsed: Variant = JSON.parse_string(text)
if parsed is Dictionary:
return parsed
push_error("SaveGame: '%s' does not contain a JSON object." % path)
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 _is_dead: bool = false
func take_damage(amount: int) -> void:
if _is_dead or amount <= 0:
return
var old_value: int = health
health = maxi(health - amount, 0)
if health != old_value:
health_changed.emit(old_value, health)
if health == 0 and not _is_dead:
_is_dead = 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
## Emitted when the fade out has finished.
signal faded
## Fades the node's modulate alpha from 1 to 0 over [param duration] seconds,
## then emits [signal faded].
func fade_out(duration: float) -> void:
var tween := create_tween()
tween.tween_property(self, "modulate:a", 0.0, duration).from(1.0)
tween.tween_callback(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
const MAX_SPAWNS: int = 4
const SPAWN_INTERVAL: float = 0.25
func _ready() -> void:
_timer = Timer.new()
_timer.wait_time = SPAWN_INTERVAL
_timer.one_shot = false
_timer.timeout.connect(_on_timer_timeout)
add_child(_timer)
_timer.start()
func _on_timer_timeout() -> void:
if spawned_count >= MAX_SPAWNS:
_timer.stop()
return
var child := Node2D.new()
add_child(child)
spawned_count += 1
if spawned_count >= MAX_SPAWNS:
_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 State { CLOSED, OPENING, OPEN }
var _state: State = State.CLOSED
var _timer: Timer
func _ready() -> void:
_timer = Timer.new()
_timer.wait_time = 0.5
_timer.one_shot = true
_timer.timeout.connect(_on_timer_timeout)
add_child(_timer)
func interact() -> void:
if _state == State.CLOSED:
_state = State.OPENING
_timer.start()
func _on_timer_timeout() -> void:
_state = State.OPEN
func get_state_name() -> String:
return State.keys()[_state]
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:
if count <= 0:
return
_items[item_name] = _items.get(item_name, 0) + count
func remove_item(item_name: String, count: int) -> bool:
if count <= 0:
return true
var current: int = _items.get(item_name, 0)
if current < count:
return false
var remaining: int = current - count
if remaining <= 0:
_items.erase(item_name)
else:
_items[item_name] = remaining
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: PackedScene = load(path)
if scene == null:
push_error("Failed to load scene at path: %s" % path)
return null
var instance: Node = scene.instantiate()
add_child(instance)
return instance
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
## Sets the cells from (from_x, y) to (to_x, y) inclusive to tile
## source 0, atlas coordinates (0, 0).
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))
## Returns whether a cell has a tile.
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
## Provides line-of-sight raycasting against the 2D physics world.
## Casts a physics ray from [param from] to [param to] and returns the
## position of the first collider hit, or [param to] if nothing is hit.
## Must be called during physics processing, when the physics space is
## accessible.
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
const DIRECTIONS: Array[Vector2i] = [
Vector2i(1, 0),
Vector2i(-1, 0),
Vector2i(0, 1),
Vector2i(0, -1),
]
func find_path(size: Vector2i, walls: Array[Vector2i], from: Vector2i, to: Vector2i) -> Array[Vector2i]:
var path: Array[Vector2i] = []
if size.x <= 0 or size.y <= 0:
return path
if not _is_in_bounds(from, size) or not _is_in_bounds(to, size):
return path
var wall_set := {}
for wall in walls:
wall_set[wall] = true
if wall_set.has(from) or wall_set.has(to):
return path
# Breadth-first search: guarantees the shortest path on an unweighted grid.
var came_from := {}
var visited := {from: true}
var queue: Array[Vector2i] = [from]
var head := 0
var found := false
while head < queue.size():
var current: Vector2i = queue[head]
head += 1
if current == to:
found = true
break
for direction in DIRECTIONS:
var next: Vector2i = current + direction
if not _is_in_bounds(next, size):
continue
if wall_set.has(next) or visited.has(next):
continue
visited[next] = true
came_from[next] = current
queue.append(next)
if not found:
return path
# Reconstruct the path from `to` back to `from`, then reverse it.
var cell := to
path.append(cell)
while cell != from:
cell = came_from[cell]
path.append(cell)
path.reverse()
return path
func _is_in_bounds(cell: Vector2i, size: Vector2i) -> bool:
return cell.x >= 0 and cell.y >= 0 and cell.x < size.x and cell.y < size.y
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 player := AnimationPlayer.new()
player.name = "AnimationPlayer"
add_child(player)
var anim := Animation.new()
anim.length = 1.0
anim.loop_mode = Animation.LOOP_LINEAR
var track := anim.add_track(Animation.TYPE_VALUE)
anim.track_set_path(track, ".:visible")
anim.value_track_set_update_mode(track, Animation.UPDATE_DISCRETE)
anim.track_insert_key(track, 0.0, true)
anim.track_insert_key(track, 0.5, false)
var library := AnimationLibrary.new()
library.add_animation("blink", anim)
player.add_animation_library("", library)
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
## Waits until [param sig] is emitted or [param seconds] of game time pass,
## whichever happens first.
##
## Returns [code]true[/code] if [param sig] was emitted before the time ran
## out, or [code]false[/code] if the wait timed out. The signal is expected
## to have no arguments. Must be called on a node inside the scene tree.
class _Race:
signal finished
func wait_for(sig: Signal, seconds: float) -> bool:
var race := _Race.new()
# Lambdas capture locals by value, so share mutable state via a Dictionary.
var state := {"resolved": false, "signaled": false}
var resolve := func(signaled: bool) -> void:
if state.resolved:
return
state.resolved = true
state.signaled = signaled
race.finished.emit()
var on_signal: Callable = resolve.bind(true)
sig.connect(on_signal, CONNECT_ONE_SHOT)
get_tree().create_timer(seconds).timeout.connect(resolve.bind(false), CONNECT_ONE_SHOT)
if not state.resolved:
await race.finished
# If the timeout won, drop the still-pending signal connection.
if sig.is_connected(on_signal):
sig.disconnect(on_signal)
return state.signaled
Questions
- Is Kimi K3 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.
Related
- Claude Haiku 5.5 on the same tasks
- Claude Opus 5.5 on the same tasks
- Claude Sonnet 5.5 on the same tasks
- DeepSeek V4.1 Flash on the same tasks
- Ember-1 on the same tasks
- Gemini 3.1 Pro Preview on the same tasks
- GLM 5.2 on the same tasks
- GPT-5.6 Luna on the same tasks
- Every verified Godot 4 answer
- Can Muse Wonder write working Godot 4 code? 15 of 15 on the first try
- Can Pareto 26.10 write working Godot 4 code? 15 of 15 on the first try
- Can MiniMax M3 write working Godot 4 code? 13 of 15 on the first try
- Can GPT-6 Luna write working Godot 4 code? 15 of 15 on the first try
- Can GPT-5.4 write working Godot 4 code? 14 of 15 on the first try
Flockbay runs your own agent, Claude or ChatGPT on the official Godot 4.7.2, and gives it Godot's errors the way this test does.
Download Flockbay free