Can GLM 5.2 write working Godot 4 code? 14 of 15 on the first try
By Eduardo Orellana · Updated
GLM 5.2 passed 14 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: wait for a signal or a timeout.
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. GLM 5.2 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.
GLM 5.2 in Flockbay
GLM 5.2 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 10.4 times as fast as Auto.
It takes text only, so Flockbay describes the game to it rather than showing screenshots, 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: float = 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: " + str(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("Could not open file for writing at path: " + path + " - Error: " + str(FileAccess.get_open_error()))
return
var json_string := JSON.stringify(data, " ")
file.store_string(json_string)
file.close()
static func load_data(path: String) -> Dictionary:
var file := FileAccess.open(path, FileAccess.READ)
if file == null:
push_error("Could not open file for reading at path: " + path + " - Error: " + str(FileAccess.get_open_error()))
return {}
var json_string := file.get_as_text()
file.close()
var parsed = JSON.parse_string(json_string)
if typeof(parsed) != TYPE_DICTIONARY:
push_error("Failed to parse JSON or JSON is not a Dictionary at path: " + path)
return {}
return parsed
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:
if amount <= 0 or _has_died:
return
var old_health := health
health = max(0, health - amount)
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)
tween.tween_callback(func(): 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 _spawn_timer: Timer
func _ready() -> void:
_spawn_timer = Timer.new()
_spawn_timer.wait_time = 0.25
_spawn_timer.timeout.connect(_on_spawn_timer_timeout)
add_child(_spawn_timer)
_spawn_timer.start()
func _on_spawn_timer_timeout() -> void:
if spawned_count >= 4:
_spawn_timer.stop()
return
var new_child := Node2D.new()
add_child(new_child)
spawned_count += 1
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 = null
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 get_state_name() -> String:
return State.keys()[_state]
func _on_timer_timeout() -> void:
if _state == State.OPENING:
_state = State.OPEN
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
class_name Inventory
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_count = _items.get(item_name, 0)
if current_count < count:
return false
var new_count = current_count - count
if new_count == 0:
_items.erase(item_name)
else:
_items[item_name] = new_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 packed_scene := load(path) as PackedScene
if packed_scene == null:
push_error("Failed to load level scene at path: " + path)
return null
var instance := packed_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
func paint_row(y: int, from_x: int, to_x: int) -> void:
var start_x: int = min(from_x, to_x)
var end_x: int = max(from_x, to_x)
for x in range(start_x, end_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 world_2d := get_world_2d()
if not world_2d:
return to
var space_state := world_2d.direct_space_state
var query := PhysicsRayQueryParameters2D.create(from, to)
var result := 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
## Finds the shortest path of grid cells from `from` to `to` (both included)
## on a grid of `size` cells, avoiding wall cells.
## Movement is limited to up, down, left, right (4-directional).
func find_path(size: Vector2i, walls: Array[Vector2i], from: Vector2i, to: Vector2i) -> Array[Vector2i]:
var path: Array[Vector2i] = []
# Bounds check.
if from.x < 0 or from.y < 0 or from.x >= size.x or from.y >= size.y:
return path
if to.x < 0 or to.y < 0 or to.x >= size.x or to.y >= size.y:
return path
# Wall set for fast lookup.
var wall_set: Dictionary = {}
for w in walls:
if w.x >= 0 and w.y >= 0 and w.x < size.x and w.y < size.y:
wall_set[w] = true
# If start or end is a wall, no path.
if wall_set.has(from) or wall_set.has(to):
return path
# Trivial case.
if from == to:
path.append(from)
return path
var directions: Array[Vector2i] = [
Vector2i(0, -1), # up
Vector2i(0, 1), # down
Vector2i(-1, 0), # left
Vector2i(1, 0), # right
]
# BFS.
var visited: Dictionary = {}
visited[from] = true
var came_from: Dictionary = {}
var queue: Array[Vector2i] = [from]
while not queue.is_empty():
var current: Vector2i = queue.pop_front()
for d in directions:
var next: Vector2i = current + d
if next.x < 0 or next.y < 0 or next.x >= size.x or next.y >= size.y:
continue
if wall_set.has(next):
continue
if visited.has(next):
continue
visited[next] = true
came_from[next] = current
if next == to:
# Reconstruct path.
var c: Vector2i = next
while c != from:
path.push_front(c)
c = came_from[c]
path.push_front(from)
return path
queue.push_back(next)
return path
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:
# Create the AnimationPlayer and add it as a child
var anim_player := AnimationPlayer.new()
add_child(anim_player)
# Create the Animation resource
var anim := Animation.new()
# Add a value track for the 'visible' property of this Node2D
var track_idx := anim.add_track(Animation.TYPE_VALUE)
anim.track_set_path(track_idx, ".:visible")
# Insert keys: visible at 0.0s, hidden at 0.5s, visible again at 1.0s for seamless looping
anim.track_insert_key(track_idx, 0.0, true)
anim.track_insert_key(track_idx, 0.5, false)
anim.track_insert_key(track_idx, 1.0, true)
# Set animation length and loop mode
anim.length = 1.0
anim.loop_mode = Animation.LOOP_LINEAR
# Create an AnimationLibrary to hold the animation
var lib := AnimationLibrary.new()
lib.add_animation("blink", anim)
# Add the library to the AnimationPlayer (using the default empty name "")
anim_player.add_animation_library("", lib)
# Play the animation
anim_player.play("blink")
Wait for a signal or a timeout: pass after one fix
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.
Failed on the first try (BENCH FAIL: returned false for a signal 0.2 s away with a 1 s timeout), passed after one fix.
What Godot 4.7.2 printed on the first try:
Godot Engine v4.7.2.stable.mono.official.ed1daf0bf - https://godotengine.org
SCRIPT ERROR: Invalid access to property or key 'resolved' on a base object of type 'Object'.
at: wait_for (res://waiter.gd:28)
GDScript backtrace (most recent call first):
[0] wait_for (res://waiter.gd:28)
[1] _ready (res://bench_check.gd:13)
SCRIPT ERROR: Invalid access to property or key 'resolved' on a base object of type 'Object'.
at: wait_for (res://waiter.gd:28)
GDScript backtrace (most recent call first):
[0] wait_for (res://waiter.gd:28)
[1] _ready (res://bench_check.gd:17)
BENCH FAIL: returned false for a signal 0.2 s away with a 1 s timeout
WARNING: 2 ObjectDB instances were leaked at exit (run with `--verbose` for details).
at: cleanup (core/object/object.cpp:2536)Questions
- Is GLM 5.2 good at Godot?
- On these 15 tasks it passed 14 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
- GPT-5.6 Luna on the same tasks
- GPT-6 Luna on the same tasks
- Every verified Godot 4 answer
- Can GPT-5.4 write working Godot 4 code? 14 of 15 on the first try
- Can DeepSeek V4 Pro 0813 write working Godot 4 code? 14 of 15 on the first try
- Can Claude Haiku 4.5 write working Godot 4 code? 11 of 15 on the first try
- Can Beam 1.0 501B A23B write working Godot 4 code? 12 of 15 on the first try
- Can MiniMax M3 write working Godot 4 code? 13 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