For a couple of weeks now, the tech community has been getting surprised by all these new AI models hitting the market every few days.
But here's the issue: most devs aren’t sure which AI model to use when it comes to working with code on a daily basis.
Just a few days ago, Anthropic released their most intelligent hybrid reasoning model yet, which they claim to be the best for coding.
But let’s see how it compares against two of our finest models, Grok 3 and o3-mini-high.
TL;DR
If you want to jump straight to the conclusion, when compared against these three models, Claude 3.7 Sonnet is the clear winner when it comes to writing code.
Grok 3 and o3-mini-high are somewhat similar, but if I had to compare them against each other, I would say Grok 3 generates slightly better code than the o3-mini-high model.
Brief on Claude 3.7 Sonnet
This AI Model just got released a few days back and is already the talk of the "tech" community. I’m emphasizing tech because this model is widely regarded as the best AI model for code, at least for now.
You can check out this video by bycloud to get a brief overview on this model's power.
Claude 3.7 Sonnet supports up to 128K output tokens (beta) which is over 15x longer than before. This is especially handy when doing longer and high quality code generation.
It's eating all the other AI models on the SWE Benchmark with an average accuracy of 62.3%. Its accuracy can even exceed 70%, the highest of any AI model to date. This represents a 13–20% accuracy gap compared to top OpenAI models, the previous Anthropic model Claude 3.5, and open-source models like DeepSeek R1.
Despite this power, Claude 3.7 has 18% reduction in total costs compared to its earlier models. It maintains consistent token-based pricing at $3 per million input tokens and $15 per million output tokens.
Not just that, Anthropic released Claude Code along with it, an agentic AI CLI that understands your codebase, helps fix issues, answers questions, and helps you get idea of your project history with its Git integration.
Check out this video to get a brief understanding of it:
Comparing These Models on Their Coding Abilities
💁♂️ Personally, though, I have really high hopes for the Claude 3.7 Sonnet. Let's see if we can spot any major differences in code between Sonnet and the other two models.
Let's start with something interesting:
1. Build simple Minecraft using Pygame
The task is simple, all the three LLMs are asked to build a simple minecraft game using Pygame.
Prompt: Build me a very simple minecraft game using Pygame in Python.
Response from Claude 3.7 Sonnet
Here's the code it generated:
import randomimport sysimport pygame# Initialize Pygamepygame.init()# Game settingsSCREEN_WIDTH = 800SCREEN_HEIGHT = 600BLOCK_SIZE = 40GRAVITY = 0.5JUMP_STRENGTH = 10PLAYER_SPEED = 5# ColorsSKY_COLOR = (135, 206, 235)PLAYER_COLOR = (255, 0, 0)GRASS_COLOR = (34, 139, 34)DIRT_COLOR = (139, 69, 19)STONE_COLOR = (105, 105, 105)COAL_COLOR = (47, 47, 47)INVENTORY_BG = (64, 64, 64, 128)# Create screenscreen = pygame.display.set_mode((SCREEN_WIDTH, SCREEN_HEIGHT))pygame.display.set_caption("Simple Minecraft")clock = pygame.time.Clock()# Block typesEMPTY = 0GRASS = 1DIRT = 2STONE = 3COAL = 4# Block colorsblock_colors = { GRASS: GRASS_COLOR, DIRT: DIRT_COLOR, STONE: STONE_COLOR, COAL: COAL_COLOR,}# Define playerclass Player: def __init__(self, x, y): self.rect = pygame.Rect(x, y, BLOCK_SIZE - 10, int(BLOCK_SIZE * 1.5)) self.velocity_y = 0 self.on_ground = False self.selected_block = GRASS def move(self, dx, dy, blocks): # Move horizontally self.rect.x += dx self.check_collision(dx, 0, blocks) # Apply gravity self.velocity_y += GRAVITY self.rect.y += int(self.velocity_y) self.on_ground = False self.check_collision(0, self.velocity_y, blocks) # Keep player on screen if self.rect.left < 0: self.rect.left = 0 if self.rect.right > SCREEN_WIDTH: self.rect.right = SCREEN_WIDTH def check_collision(self, dx, dy, blocks): for y, row in enumerate(blocks): for x, block in enumerate(row): if block != EMPTY: block_rect = pygame.Rect( x * BLOCK_SIZE, y * BLOCK_SIZE, BLOCK_SIZE, BLOCK_SIZE ) if self.rect.colliderect(block_rect): if dx > 0: # Moving right self.rect.right = block_rect.left if dx < 0: # Moving left self.rect.left = block_rect.right if dy > 0: # Moving down self.rect.bottom = block_rect.top self.on_ground = True self.velocity_y = 0 if dy < 0: # Moving up self.rect.top = block_rect.bottom self.velocity_y = 0 def jump(self): if self.on_ground: self.velocity_y = -JUMP_STRENGTH def draw(self, surface): pygame.draw.rect(surface, PLAYER_COLOR, self.rect)# Create worlddef create_world(width, height): world = [[EMPTY for _ in range(width)] for _ in range(height)] # Generate terrain ground_height = height - 5 for x in range(width): height_variation = random.randint(-1, 1) ground_height += height_variation # Keep within bounds if ground_height < height - 10: ground_height = height - 10 if ground_height > height - 3: ground_height = height - 3 # Add grass at the top world[ground_height][x] = GRASS # Add dirt below grass for y in range(ground_height + 1, ground_height + 4): if y < height: world[y][x] = DIRT # Add stone below dirt for y in range(ground_height + 4, height): if y < height: if random.random() < 0.1: # 10% chance for coal world[y][x] = COAL else: world[y][x] = STONE return world# Initialize gameworld_width = SCREEN_WIDTH // BLOCK_SIZEworld_height = SCREEN_HEIGHT // BLOCK_SIZEworld = create_world(world_width, world_height)player = Player(SCREEN_WIDTH // 2, 0)# Game looprunning = Truewhile running: for event in pygame.event.get(): if event.type == pygame.QUIT: running = False # Jump on space if event.type == pygame.KEYDOWN: if event.key == pygame.K_SPACE: player.jump() # Switch selected block if event.key == pygame.K_1: player.selected_block = GRASS elif event.key == pygame.K_2: player.selected_block = DIRT elif event.key == pygame.K_3: player.selected_block = STONE elif event.key == pygame.K_4: player.selected_block = COAL # Place or break blocks with mouse if event.type == pygame.MOUSEBUTTONDOWN: mouse_x, mouse_y = pygame.mouse.get_pos() block_x = mouse_x // BLOCK_SIZE block_y = mouse_y // BLOCK_SIZE # Make sure it's within world bounds if 0 <= block_x < world_width and 0 <= block_y < world_height: # Left click to place block if event.button == 1: # Don't place if player is there block_rect = pygame.Rect( block_x * BLOCK_SIZE, block_y * BLOCK_SIZE, BLOCK_SIZE, BLOCK_SIZE, ) if not player.rect.colliderect(block_rect): world[block_y][block_x] = player.selected_block # Right click to break block elif event.button == 3: world[block_y][block_x] = EMPTY # Handle movement keys = pygame.key.get_pressed() dx = 0 if keys[pygame.K_a] or keys[pygame.K_LEFT]: dx = -PLAYER_SPEED if keys[pygame.K_d] or keys[pygame.K_RIGHT]: dx = PLAYER_SPEED player.move(dx, 0, world) # Draw everything screen.fill(SKY_COLOR) # Draw blocks for y, row in enumerate(world): for x, block in enumerate(row): if block != EMPTY: pygame.draw.rect( screen, block_colors[block], (x * BLOCK_SIZE, y * BLOCK_SIZE, BLOCK_SIZE, BLOCK_SIZE), ) # Draw player player.draw(screen) # Draw inventory pygame.draw.rect(screen, INVENTORY_BG, (10, 10, 200, 50)) for i, block_type in enumerate([GRASS, DIRT, STONE, COAL]): block_rect = pygame.Rect(20 + i * 50, 15, 40, 40) pygame.draw.rect(screen, block_colors[block_type], block_rect) # Highlight selected block if block_type == player.selected_block: pygame.draw.rect(screen, (255, 255, 255), block_rect, 2) # Draw number font = pygame.font.SysFont(None, 24) text = font.render(str(i + 1), True, (255, 255, 255)) screen.blit(text, (block_rect.x + 5, block_rect.y + 5)) # Update display pygame.display.flip() clock.tick(60)pygame.quit()sys.exit()
Here's the output of the program:
Response from Grok 3
Here's the code it generated:
import pygame# Initialize Pygamepygame.init()# Screen settingsWIDTH = 800HEIGHT = 600BLOCK_SIZE = 40screen = pygame.display.set_mode((WIDTH, HEIGHT))pygame.display.set_caption("Simple Minecraft 2D")# ColorsWHITE = (255, 255, 255)BLACK = (0, 0, 0)BROWN = (139, 69, 19)GREEN = (0, 255, 0)BLUE = (0, 0, 255)# Player classclass Player: def __init__(self, x, y): self.x = x self.y = y self.width = BLOCK_SIZE self.height = BLOCK_SIZE self.speed = 5 def draw(self): pygame.draw.rect(screen, BLUE, (self.x, self.y, self.width, self.height))# Block classclass Block: def __init__(self, x, y, block_type): self.x = x self.y = y self.width = BLOCK_SIZE self.height = BLOCK_SIZE self.type = block_type def draw(self): if self.type == "dirt": pygame.draw.rect(screen, BROWN, (self.x, self.y, self.width, self.height)) elif self.type == "grass": pygame.draw.rect(screen, GREEN, (self.x, self.y, self.width, self.height))# Create game objectsplayer = Player(WIDTH // 2, HEIGHT // 2)blocks = []# Generate initial terrainfor x in range(0, WIDTH, BLOCK_SIZE): for y in range(HEIGHT // 2, HEIGHT, BLOCK_SIZE): if y == HEIGHT // 2: blocks.append(Block(x, y, "grass")) else: blocks.append(Block(x, y, "dirt"))# Game loopclock = pygame.time.Clock()running = Trueinventory = []while running: for event in pygame.event.get(): if event.type == pygame.QUIT: running = False elif event.type == pygame.MOUSEBUTTONDOWN: mouse_x, mouse_y = pygame.mouse.get_pos() # Left click to break block if event.button == 1: for block in blocks[:]: if ( block.x <= mouse_x < block.x + BLOCK_SIZE and block.y <= mouse_y < block.y + BLOCK_SIZE ): inventory.append(block.type) blocks.remove(block) break # Right click to place block elif event.button == 3 and inventory: grid_x = (mouse_x // BLOCK_SIZE) * BLOCK_SIZE grid_y = (mouse_y // BLOCK_SIZE) * BLOCK_SIZE # Check if space is empty occupied = False for block in blocks: if block.x == grid_x and block.y == grid_y: occupied = True break if not occupied and grid_y >= HEIGHT // 2: blocks.append(Block(grid_x, grid_y, inventory.pop())) # Player movement keys = pygame.key.get_pressed() if keys[pygame.K_LEFT] and player.x > 0: player.x -= player.speed if keys[pygame.K_RIGHT] and player.x < WIDTH - player.width: player.x += player.speed if keys[pygame.K_UP] and player.y > 0: player.y -= player.speed if keys[pygame.K_DOWN] and player.y < HEIGHT - player.height: player.y += player.speed # Draw everything screen.fill(WHITE) for block in blocks: block.draw() player.draw() # Display inventory font = pygame.font.Font(None, 36) text = font.render(f"Inventory: {len(inventory)} blocks", True, BLACK) screen.blit(text, (10, 10)) pygame.display.flip() clock.tick(60)pygame.quit()
Here's the output of the program:
This program we got is pretty disappointing and definitely not what I expected. Nothing works as it should, except player movement. It looks way less like Minecraft and more like a snake game. 😮💨
Response from OpenAI o3-mini-high
Here's the code it generated:
import pygame# Initialize Pygamepygame.init()# Screen settingsWIDTH = 800HEIGHT = 600BLOCK_SIZE = 40screen = pygame.display.set_mode((WIDTH, HEIGHT))pygame.display.set_caption("Simple Minecraft 2D")# ColorsWHITE = (255, 255, 255)BLACK = (0, 0, 0)BROWN = (139, 69, 19)GREEN = (0, 255, 0)BLUE = (0, 0, 255)# Player classclass Player: def __init__(self, x, y): self.x = x self.y = y self.width = BLOCK_SIZE self.height = BLOCK_SIZE self.speed = 5 def draw(self): pygame.draw.rect(screen, BLUE, (self.x, self.y, self.width, self.height))# Block classclass Block: def __init__(self, x, y, block_type): self.x = x self.y = y self.width = BLOCK_SIZE self.height = BLOCK_SIZE self.type = block_type def draw(self): if self.type == "dirt": pygame.draw.rect(screen, BROWN, (self.x, self.y, self.width, self.height)) elif self.type == "grass": pygame.draw.rect(screen, GREEN, (self.x, self.y, self.width, self.height))# Create game objectsplayer = Player(WIDTH // 2, HEIGHT // 2)blocks = []# Generate initial terrainfor x in range(0, WIDTH, BLOCK_SIZE): for y in range(HEIGHT // 2, HEIGHT, BLOCK_SIZE): if y == HEIGHT // 2: blocks.append(Block(x, y, "grass")) else: blocks.append(Block(x, y, "dirt"))# Game loopclock = pygame.time.Clock()running = Trueinventory = []while running: for event in pygame.event.get(): if event.type == pygame.QUIT: running = False elif event.type == pygame.MOUSEBUTTONDOWN: mouse_x, mouse_y = pygame.mouse.get_pos() # Left click to break block if event.button == 1: for block in blocks[:]: if ( block.x <= mouse_x < block.x + BLOCK_SIZE and block.y <= mouse_y < block.y + BLOCK_SIZE ): inventory.append(block.type) blocks.remove(block) break # Right click to place block elif event.button == 3 and inventory: grid_x = (mouse_x // BLOCK_SIZE) * BLOCK_SIZE grid_y = (mouse_y // BLOCK_SIZE) * BLOCK_SIZE # Check if space is empty occupied = False for block in blocks: if block.x == grid_x and block.y == grid_y: occupied = True break if not occupied and grid_y >= HEIGHT // 2: blocks.append(Block(grid_x, grid_y, inventory.pop())) # Player movement keys = pygame.key.get_pressed() if keys[pygame.K_LEFT] and player.x > 0: player.x -= player.speed if keys[pygame.K_RIGHT] and player.x < WIDTH - player.width: player.x += player.speed if keys[pygame.K_UP] and player.y > 0: player.y -= player.speed if keys[pygame.K_DOWN] and player.y < HEIGHT - player.height: player.y += player.speed # Draw everything screen.fill(WHITE) for block in blocks: block.draw() player.draw() # Display inventory font = pygame.font.Font(None, 36) text = font.render(f"Inventory: {len(inventory)} blocks", True, BLACK) screen.blit(text, (10, 10)) pygame.display.flip() clock.tick(60)pygame.quit()
Here's the output of the program:
The output by the o3-mini-high model is pretty disappointing, all that we got is a blank screen with added background color. 🤦♂️
Final Verdict: It's pretty fair to say Claude 3.7 wins by a huge margin. ✅ Everything works just as expected. The overall game it built includes almost all the features I thought for.
2. Multiple Balls in a Spinning Hexagon
Let's do a quick test of all these models with a pretty standard question used to judge different LLMs.
This is a modified version of the question where only one ball is spun up inside a spinning hexagon.
Prompt: Write me a Python script for 10 balls inside a fast spinning hexagon.
Response from Claude 3.7 Sonnet
Here's the code it generated:
import mathimport randomimport sysimport pygame# Initialize pygamepygame.init()# ConstantsWIDTH, HEIGHT = 800, 600FPS = 60WHITE = (255, 255, 255)BLACK = (0, 0, 0)GRAY = (100, 100, 100)BALL_COLORS = [ (255, 0, 0), # Red (0, 255, 0), # Green (0, 0, 255), # Blue (255, 255, 0), # Yellow (255, 0, 255), # Magenta (0, 255, 255), # Cyan (255, 165, 0), # Orange (128, 0, 128), # Purple (255, 192, 203), # Pink (0, 128, 0), # Dark Green]# Screen setupscreen = pygame.display.set_mode((WIDTH, HEIGHT))pygame.display.set_caption("Multiple Balls in a Fast-Spinning Hexagon")clock = pygame.time.Clock()# Hexagon propertieshex_radius = 180hex_center = (WIDTH // 2, HEIGHT // 2)hex_rotation = 0hex_rotation_speed = 2.0 # Increased speed (degrees per frame)# Ball propertiesnum_balls = 10ball_radius = 15balls = []# Create balls with random positions and velocitiesfor i in range(num_balls): # Random position inside the hexagon (with some margin from the edges) angle = random.uniform(0, 2 * math.pi) distance = random.uniform(0, hex_radius - ball_radius * 2) x = hex_center[0] + distance * math.cos(angle) y = hex_center[1] + distance * math.sin(angle) # Random velocity velocity_x = random.uniform(-3, 3) velocity_y = random.uniform(-3, 3) balls.append( { "pos": [x, y], "velocity": [velocity_x, velocity_y], "color": BALL_COLORS[i], "radius": ball_radius, } )# Function to calculate hexagon verticesdef get_hexagon_vertices(center, radius, rotation): vertices = [] for i in range(6): angle_deg = rotation + 60 * i angle_rad = math.radians(angle_deg) x = center[0] + radius * math.cos(angle_rad) y = center[1] + radius * math.sin(angle_rad) vertices.append((x, y)) return vertices# Function to check collision with a line segmentdef check_line_collision(ball_pos, ball_radius, line_start, line_end): x1, y1 = line_start x2, y2 = line_end x0, y0 = ball_pos # Vector from line start to end dx, dy = x2 - x1, y2 - y1 # Vector from line start to ball dx0, dy0 = x0 - x1, y0 - y1 # Calculate projection length t = max(0, min(1, (dx0 * dx + dy0 * dy) / (dx * dx + dy * dy))) # Calculate closest point on the line closest_x = x1 + t * dx closest_y = y1 + t * dy # Distance from ball to closest point distance = math.sqrt((x0 - closest_x) ** 2 + (y0 - closest_y) ** 2) # Return collision info if distance <= ball_radius: # Normal vector for reflection if distance > 0: # Avoid division by zero nx = (x0 - closest_x) / distance ny = (y0 - closest_y) / distance else: nx, ny = 0, -1 # Default normal if distance is zero return True, (nx, ny) return False, None# Function to check collision between ballsdef check_ball_collision(ball1, ball2): x1, y1 = ball1["pos"] x2, y2 = ball2["pos"] # Distance between balls distance = math.sqrt((x2 - x1) ** 2 + (y2 - y1) ** 2) # If balls are colliding if distance <= (ball1["radius"] + ball2["radius"]): # Normal vector if distance > 0: nx = (x2 - x1) / distance ny = (y2 - y1) / distance else: nx, ny = 0, 1 # Default if balls are at the same position return True, (nx, ny) return False, None# Main game loopgravity = 0.1ball_speed_limit = 6running = Truewhile running: for event in pygame.event.get(): if event.type == pygame.QUIT: running = False # Update hexagon rotation hex_rotation += hex_rotation_speed if hex_rotation >= 360: hex_rotation -= 360 # Get hexagon vertices hex_vertices = get_hexagon_vertices(hex_center, hex_radius, hex_rotation) # Update balls for ball in balls: # Apply gravity ball["velocity"][1] += gravity # Update ball position ball["pos"][0] += ball["velocity"][0] ball["pos"][1] += ball["velocity"][1] # Check collision with hexagon sides for i in range(6): start = hex_vertices[i] end = hex_vertices[(i + 1) % 6] collision, normal = check_line_collision( ball["pos"], ball["radius"], start, end ) if collision: # Reflect velocity across the normal nx, ny = normal dot_product = ball["velocity"][0] * nx + ball["velocity"][1] * ny ball["velocity"][0] -= 2 * dot_product * nx ball["velocity"][1] -= 2 * dot_product * ny # Apply some energy loss ball["velocity"][0] *= 0.9 ball["velocity"][1] *= 0.9 # Move ball away from the wall to avoid getting stuck ball["pos"][0] += nx * 2 ball["pos"][1] += ny * 2 # Limit ball speed speed = math.sqrt(ball["velocity"][0] ** 2 + ball["velocity"][1] ** 2) if speed > ball_speed_limit: ball["velocity"][0] = (ball["velocity"][0] / speed) * ball_speed_limit ball["velocity"][1] = (ball["velocity"][1] / speed) * ball_speed_limit # Check collisions between balls for i in range(num_balls): for j in range(i + 1, num_balls): collision, normal = check_ball_collision(balls[i], balls[j]) if collision: # Calculate relative velocity nx, ny = normal vx1, vy1 = balls[i]["velocity"] vx2, vy2 = balls[j]["velocity"] # Relative velocity along the normal vrn = (vx1 - vx2) * nx + (vy1 - vy2) * ny # If balls are moving away from each other, skip if vrn < 0: continue # Mass (assume equal mass) m1 = 1.0 m2 = 1.0 # Elastic collision response impulse = 2.0 * vrn / (m1 + m2) # Update velocities balls[i]["velocity"][0] -= impulse * m2 * nx balls[i]["velocity"][1] -= impulse * m2 * ny balls[j]["velocity"][0] += impulse * m1 * nx balls[j]["velocity"][1] += impulse * m1 * ny # Move balls apart to avoid sticking overlap = ( balls[i]["radius"] + balls[j]["radius"] - math.sqrt( (balls[i]["pos"][0] - balls[j]["pos"][0]) ** 2 + (balls[i]["pos"][1] - balls[j]["pos"][1]) ** 2 ) ) if overlap > 0: # Move proportional to their velocities balls[i]["pos"][0] -= nx * overlap * 0.5 balls[i]["pos"][1] -= ny * overlap * 0.5 balls[j]["pos"][0] += nx * overlap * 0.5 balls[j]["pos"][1] += ny * overlap * 0.5 # Draw everything screen.fill(BLACK) # Draw hexagon pygame.draw.polygon(screen, GRAY, hex_vertices, 3) # Draw balls for ball in balls: pygame.draw.circle( screen, ball["color"], (int(ball["pos"][0]), int(ball["pos"][1])), ball["radius"], ) pygame.display.flip() clock.tick(FPS)pygame.quit()sys.exit()
The code has just a few minor issues, like how we are extracting values from the normal returned by the check_ball_collision method without checking if the value is None.
Other than that, everything looks quite good.
Here's the output of the program:
Response from Grok 3
Here's the code it generated:
import mathimport randomimport pygame# Initialize Pygamepygame.init()# Set up the displayWIDTH = 800HEIGHT = 600screen = pygame.display.set_mode((WIDTH, HEIGHT))pygame.display.set_caption("Balls in Spinning Hexagon")# ColorsWHITE = (255, 255, 255)RED = (255, 0, 0)BLUE = (0, 0, 255)# Hexagon propertiescenter_x = WIDTH // 2center_y = HEIGHT // 2hex_size = 200hex_angle = 0hex_speed = 0.05 # radians per frame# Ball propertiesclass Ball: def __init__(self): self.radius = 10 self.x = center_x self.y = center_y self.dx = random.uniform(-3, 3) self.dy = random.uniform(-3, 3) self.color = ( random.randint(0, 255), random.randint(0, 255), random.randint(0, 255), )# Create ballsballs = [Ball() for _ in range(10)]# Get hexagon verticesdef get_hexagon_vertices(x, y, size, angle): vertices = [] for i in range(6): vertex_angle = angle + (math.pi / 3) * i vx = x + size * math.cos(vertex_angle) vy = y + size * math.sin(vertex_angle) vertices.append((vx, vy)) return vertices# Check collision with hexagon wallsdef check_collision(ball, vertices): for i in range(6): x1, y1 = vertices[i] x2, y2 = vertices[(i + 1) % 6] # Line equation: ax + by + c = 0 a = y2 - y1 b = x1 - x2 c = -(a * x1 + b * y1) # Distance from point to line distance = abs(a * ball.x + b * ball.y + c) / math.sqrt(a * a + b * b) if distance <= ball.radius: # Normal vector nx = b ny = -a norm_length = math.sqrt(nx * nx + ny * ny) nx /= norm_length ny /= norm_length # Reflect velocity dot = ball.dx * nx + ball.dy * ny ball.dx = ball.dx - 2 * dot * nx ball.dy = ball.dy - 2 * dot * ny # Push ball away from wall penetration = ball.radius - distance ball.x += nx * penetration ball.y += ny * penetration# Main game loopclock = pygame.time.Clock()running = Truewhile running: for event in pygame.event.get(): if event.type == pygame.QUIT: running = False # Clear screen screen.fill((0, 0, 0)) # Update hexagon rotation hex_angle += hex_speed vertices = get_hexagon_vertices(center_x, center_y, hex_size, hex_angle) # Update balls for ball in balls: # Move ball ball.x += ball.dx ball.y += ball.dy # Check collision with hexagon check_collision(ball, vertices) # Draw ball pygame.draw.circle(screen, ball.color, (int(ball.x), int(ball.y)), ball.radius) # Draw hexagon pygame.draw.polygon(screen, WHITE, vertices, 2) # Update display pygame.display.flip() clock.tick(60)pygame.quit()
Here's the output of the program:
There's an issue, the balls are not supposed to be outside of the hexagon.
When I asked it the standard question of one ball inside the spinning hexagon, it answered easily, but it couldn't handle when I tweaked it just a bit.
Fair to say, this model could not handle this question well.
Response from OpenAI o3-mini-high
Here's the code it generated:
#!/usr/bin/env python3import mathimport randomimport pygamedef get_hexagon_vertices(center, radius, angle_offset): """ Returns a list of 6 pygame.Vector2 vertices for a regular hexagon. center -- pygame.Vector2 at the center. radius -- Distance from center to a vertex. angle_offset-- Overall rotation in radians. """ vertices = [] for i in range(6): # Each vertex is 60 degrees (pi/3 radians) apart. angle = math.radians(60 * i) + angle_offset vertex = center + pygame.Vector2(math.cos(angle) * radius, math.sin(angle) * radius) vertices.append(vertex) return verticesdef point_in_poly(x, y, poly): """ Determines if point (x, y) is inside the polygon. poly is a list of (x, y) tuples. (Uses the ray-casting algorithm.) """ inside = False n = len(poly) p1x, p1y = poly[0] for i in range(n+1): p2x, p2y = poly[i % n] if (y > min(p1y, p2y)) and (y <= max(p1y, p2y)) and (x <= max(p1x, p2x)): if p1y != p2y: xinters = (y - p1y) * (p2x - p1x) / (p2y - p1y) + p1x else: xinters = p1x if p1x == p2x or x <= xinters: inside = not inside p1x, p1y = p2x, p2y return insidedef main(): pygame.init() # Window size and title width, height = 800, 600 screen = pygame.display.set_mode((width, height)) pygame.display.set_caption("10 Balls Inside a Fast Spinning Hexagon") clock = pygame.time.Clock() hex_center = pygame.Vector2(width/2, height/2) hex_radius = 200 # Distance from center to vertex. rotation_angle = 0 # Current rotation angle in radians. rotation_speed = 5 # Radians per second (fast spinning). ball_radius = 10 n_balls = 10 balls = [] # Each ball is a dictionary with keys: pos, vel, color. # Use the hexagon's initial (unrotated) vertices for placing balls. initial_vertices = get_hexagon_vertices(hex_center, hex_radius, rotation_angle) # Convert vertices to a list of (x,y) tuples for point_in_poly testing. initial_poly = [(v.x, v.y) for v in initial_vertices] # Create n_balls with random positions INSIDE the hexagon and random velocities. while len(balls) < n_balls: test_x = random.uniform(hex_center.x - hex_radius, hex_center.x + hex_radius) test_y = random.uniform(hex_center.y - hex_radius, hex_center.y + hex_radius) # Only accept if inside the polygon: if point_in_poly(test_x, test_y, initial_poly): ball = { 'pos': pygame.Vector2(test_x, test_y), # Random velocity (pixels per second). Adjust the numbers for speed. 'vel': pygame.Vector2(random.uniform(-200, 200), random.uniform(-200, 200)), 'color': (random.randint(50,255), random.randint(50,255), random.randint(50,255)) } balls.append(ball) running = True while running: dt = clock.tick(60) / 1000.0 # Delta-time in seconds. for event in pygame.event.get(): if event.type == pygame.QUIT: running = False # Optionally press ESC to quit. elif event.type == pygame.KEYDOWN and event.key == pygame.K_ESCAPE: running = False # Increase the rotation angle. rotation_angle += rotation_speed * dt # (Keep angle bounded to 2pi if you like; not strictly necessary.) rotation_angle %= (2 * math.pi) # Compute the current hexagon vertices. hex_vertices = get_hexagon_vertices(hex_center, hex_radius, rotation_angle) # For collision computations we need the “inward” normal for each edge. # For a given edge from A to B, the inward normal is chosen so that: # n = N/|N|, where N = (-(B.y-A.y), (B.x-A.x)) or its negative, # and it must point towards the hexagon center. edge_normals = [] n_edges = len(hex_vertices) for i in range(n_edges): A = hex_vertices[i] B = hex_vertices[(i+1) % n_edges] edge = B - A # Candidate normal (rotate 90 degrees) candidate = pygame.Vector2(-edge.y, edge.x) # Check – choose the normal that points toward the hexagon’s center. if candidate.dot(hex_center - A) < 0: candidate = -candidate n = candidate.normalize() edge_normals.append((A, n)) # Update each ball’s position and check for collision with each edge. for ball in balls: ball['pos'] += ball['vel'] * dt # Check collision with every edge of the hexagon. for A, n in edge_normals: # Compute how far the ball's center is along the inward normal from edge A. # (The signed distance.) d = (ball['pos'] - A).dot(n) if d < ball_radius: # Only reflect if the ball is moving against the wall. if ball['vel'].dot(n) < 0: ball['vel'] = ball['vel'] - 2 * ball['vel'].dot(n) * n # Push the ball out of penetration. ball['pos'] += (ball_radius - d) * n screen.fill((0, 0, 0)) # clear with black. # Draw the hexagon (outline only). # Convert hexagon vertices from Vector2 to tuples. hex_points = [(int(v.x), int(v.y)) for v in hex_vertices] pygame.draw.polygon(screen, (255, 255, 255), hex_points, 3) # Draw balls. for ball in balls: pos = (int(ball['pos'].x), int(ball['pos'].y)) pygame.draw.circle(screen, ball['color'], pos, ball_radius) pygame.display.flip() pygame.quit()if __name__ == "__main__": main()
Here's the output of the program:
Final Verdict: On this question, I was pretty surprised that, except for the Grok 3 model, both Claude 3.7 and o3-mini-high got the answer correct ✅. o3-mini-high seems to have outperformed Grok 3 here.
3. Build a realtime Browser-Based Markdown Editor
Considering how good Claude has been in both the tests of building a game and animation, and again with their solid claims on coding, let's do a quick web app test on all three models.
Prompt: Build a tiny browser-based Markdown editor with syntax highlighting, export-to-PDF functionality, and a minimal UI using Tailwind in Next.js, with all the changes in a single file.
The code is almost all good, except that code highlighting does not work properly. This seems to be an issue because marked recently introduced breaking changes in setting up code highlighting.
The model may not be trained on the most recent data for the module.
There are a couple of issues we’ve got, the first one being that the headings don’t really work. There are issues with the font contrast, and the exported PDF doesn’t render the Markdown properly.
Here's the output of the program:
In the exported PDF, we get raw text instead of formatted Markdown, with no emoji support.
Final Verdict: Here as well, Claude 3.7 is the clear winner compared to the other two models. ✅ Almost everything worked, but the other two models couldn't get it right. There were a couple of issues with text contrast, markdown rendering on the site and in the PDF.
4. Build a Code Diff Viewer
Let's try a simple web application example to see if all of them get it right.
This is a pretty standard question and somewhat easy to implement. I have high hopes that all three of them should get it right (even o3-mini-high 😮💨). So far, I'm somewhat disappointed with it, though.
Prompt: Write a simple web application for a code diff viewer, a tool that takes two text inputs and highlights differences side by side.
Everything else seems to be working fine with this as well, but in the diff, it is not taking the line's indentation into account.
Response from OpenAI o3-mini-high
Here's the code it generated:
"use client";import React, { JSX, useState } from "react";import { diffWords } from "diff";export default function Page() { // State for the two text inputs and for the computed diff result. const [leftText, setLeftText] = useState(""); const [rightText, setRightText] = useState(""); // diffResult stores an array of rows where each row is an object with two JSX elements: // one for the left side and one for the right side. const [diffResult, setDiffResult] = useState< { left: JSX.Element; right: JSX.Element }[] >([]); // compare the two texts line‐by‐line. const computeDiff = () => { const leftLines = leftText.split("\n"); const rightLines = rightText.split("\n"); const maxLines = Math.max(leftLines.length, rightLines.length); const results: { left: JSX.Element; right: JSX.Element }[] = []; for (let i = 0; i < maxLines; i++) { const leftLine = leftLines[i] ?? ""; const rightLine = rightLines[i] ?? ""; // If the lines are identical, display them as plain text. if (leftLine === rightLine) { results.push({ left: <span>{leftLine}</span>, right: <span>{rightLine}</span>, }); } else { const diff = diffWords(leftLine, rightLine); // For the left side, ignore the parts that were "added" // and highlight (with red) the parts that were "removed". const leftContent = diff.map((part, index) => { if (part.added) return null; return ( <span key={index} className={part.removed ? "bg-red-200" : undefined} > {part.value} </span> ); }); // For the right side, ignore the parts that were "removed" // and highlight (with green) the parts that were "added". const rightContent = diff.map((part, index) => { if (part.removed) return null; return ( <span key={index} className={part.added ? "bg-green-200" : undefined} > {part.value} </span> ); }); results.push({ left: <>{leftContent}</>, right: <>{rightContent}</>, }); } } setDiffResult(results); }; return ( <div className="min-h-screen bg-gray-50 p-8 text-black"> <h1 className="text-3xl font-bold mb-6 text-center"> Simple Code Diff Viewer </h1> {/* Two textareas side by side (stacked vertically on small screens) */} <div className="flex flex-col md:flex-row md:space-x-4"> <textarea value={leftText} onChange={(e) => setLeftText(e.target.value)} placeholder="Enter left text" className="flex-1 p-2 border border-gray-300 rounded mb-4 md:mb-0 resize-y min-h-[200px]" /> <textarea value={rightText} onChange={(e) => setRightText(e.target.value)} placeholder="Enter right text" className="flex-1 p-2 border border-gray-300 rounded resize-y min-h-[200px]" /> </div> <div className="mt-4 text-center"> <button onClick={computeDiff} className="px-4 py-2 bg-blue-500 text-white rounded hover:bg-blue-600" > Compare </button> </div> {/* Diff viewer: a grid with two columns for left and right side diff display */} <div className="mt-8 overflow-auto"> <div className="grid grid-cols-2 gap-4"> {diffResult.map((row, index) => ( <React.Fragment key={index}> <div className="p-2 border border-gray-300 bg-white min-h-[40px] whitespace-pre font-mono"> {row.left} </div> <div className="p-2 border border-gray-300 bg-white min-h-[40px] whitespace-pre font-mono"> {row.right} </div> </React.Fragment> ))} </div> </div> </div> );}
Here's the output of the program:
Here, we have an interesting result. It decided to use an external library diff and do highlighting per character and not per line.
Final Verdict: By functionality-wise, all three models got this problem correct (at least from testing at the surface level. There might be edge cases, though). I must say the overall code quality and output by o3-mini-high is comparatively better ✅ than both the Claude 3.7 Sonnet and Grok 3 model.
5. Manim code for Square to Pyramid Animation
Let's end our test with a final Manim question. Most LLMs pretty much suck at writing Manim code, and it gets even harder when it's a 3D scene.
Prompt: Create a Manim animation in Python where a 2D square smoothly lifts into 3D space to form a pyramid. Then, animate the pyramid shrinking back into a square.
Response from Claude 3.7 Sonnet
Here's the code it generated:
import numpy as npfrom manim import (BLUE, DEGREES, PI, UP, WHITE, Create, FadeOut, Polygon, Rotate, Square, ThreeDScene, VGroup)class SquareToPyramidAnimation(ThreeDScene): def construct(self): # Set up the scene self.set_camera_orientation(phi=75 * DEGREES, theta=30 * DEGREES) # Create a square square = Square(side_length=2, fill_opacity=0.7, fill_color=BLUE) # Show the square first self.play(Create(square)) self.wait(1) # Prepare for 3D transformation # Add z-coordinate to the square's points to make it compatible with 3D square_3d = square.copy() square_points = square_3d.get_vertices() # Create a pyramid pyramid = Pyramid(square_length=2, height=2) pyramid.set_fill(BLUE, opacity=0.7) pyramid.set_stroke(WHITE, width=1) # The pyramid is initially hidden pyramid.set_opacity(0) self.add(pyramid) # Animate the square to the base of the pyramid self.play( square.animate.set_opacity(0), pyramid.animate.set_opacity(0.7), run_time=2 ) # Move the camera to get a better view of the pyramid self.move_camera(phi=60 * DEGREES, theta=45 * DEGREES, run_time=2) self.wait(1) # Rotate the pyramid to showcase its 3D nature self.play(Rotate(pyramid, angle=2 * PI, axis=UP), run_time=4) self.wait(1) # Animate the pyramid shrinking back to a square self.play( pyramid.animate.set_opacity(0), square.animate.set_opacity(0.7), run_time=2 ) # Return camera to original position self.move_camera(phi=75 * DEGREES, theta=30 * DEGREES, run_time=2) self.wait(1) # Finish by fading out the square self.play(FadeOut(square)) self.wait(1)class Pyramid(VGroup): def __init__(self, square_length=2, height=2, **kwargs): super().__init__(**kwargs) # Create the base square at z=0 square = Square(side_length=square_length) square_vertices = square.get_vertices() # Apex of the pyramid at height above the center of the square apex = np.array([0, 0, height]) # Create the faces of the pyramid faces = VGroup() # Base (the square itself) base = Polygon(*square_vertices, fill_opacity=0.7, fill_color=BLUE) faces.add(base) # Side triangular faces for i in range(4): v1 = square_vertices[i] v2 = square_vertices[(i + 1) % 4] face = Polygon( v1, v2, apex, fill_opacity=0.7, fill_color=BLUE, shade_in_3d=True ) faces.add(face) self.add(faces)
Here's the output of the program:
Response from Grok 3
Here's the code it generated:
from manim import (BLUE, DEGREES, ORIGIN, WHITE, Create, FadeOut, Polygon, Square, ThreeDScene, VGroup)class SquareToPyramid(ThreeDScene): def construct(self): # Set up the 3D camera self.set_camera_orientation(phi=75 * DEGREES, theta=30 * DEGREES) # Create the initial 2D square square = Square(side_length=2, fill_opacity=0.5, fill_color=BLUE) square.move_to(ORIGIN) # Show the initial square self.play(Create(square)) self.wait(1) # Define the vertices of the square bottom_vertices = [ [-1, -1, 0], # Bottom left [1, -1, 0], # Bottom right [1, 1, 0], # Top right [-1, 1, 0], # Top left ] # Define the apex of the pyramid (will rise to this point) apex = [0, 0, 2] # Create the pyramid (tetrahedron) using Polygon for faces pyramid_faces = VGroup() for i in range(4): face = Polygon( bottom_vertices[i], bottom_vertices[(i + 1) % 4], apex, fill_opacity=0.5, fill_color=BLUE, stroke_color=WHITE, ) pyramid_faces.add(face) # Animation to transform square into pyramid # First, fade out the square while raising the apex self.begin_ambient_camera_rotation(rate=0.2) self.play(FadeOut(square), Create(pyramid_faces), run_time=2) # Rotate the pyramid to show 3D structure self.wait(2) # Shrink pyramid back to square # Create a new square for the final state final_square = Square(side_length=2, fill_opacity=0.5, fill_color=BLUE) final_square.move_to(ORIGIN) self.play(FadeOut(pyramid_faces), Create(final_square), run_time=2) # Stop camera rotation and show final result self.stop_ambient_camera_rotation() self.wait(1)
Here's the output of the program:
Response from OpenAI o3-mini-high
Here's the code it generated:
#!/usr/bin/env pythonfrom manim import (BLUE, DEGREES, GREEN, UP, Create, Line, ReplacementTransform, Square, ThreeDScene, ValueTracker, VGroup, always_redraw)class SquareToPyramid(ThreeDScene): def construct(self): # Set an initial camera orientation so the 3D effect is clear. self.set_camera_orientation(phi=70 * DEGREES, theta=-45 * DEGREES) # Create a blue square (the base, side length = 2) square = Square(side_length=2, color=BLUE) self.play(Create(square)) self.wait(1) # We'll use a ValueTracker to control the pyramid’s “apex height.” # When the value is 0, the apex is at the square’s center. # When the value is >0, the apex lifts upward (UP is the z-axis). height_tracker = ValueTracker(0) # Define a function that returns a VGroup drawing the pyramid for any given height. # It builds: # • the base (i.e. 4 lines from the square’s corners, drawn in blue) # • the 4 side edges (lines from each corner of the square up to the apex, drawn in green) def get_pyramid(height): # Get the square’s vertices (the corners); by default a Square’s vertices are ordered. corners = square.get_vertices() # Define the apex: start from the square’s center and add "height" in the upward (z) direction. apex = square.get_center() + height * UP # Create the base edges as a closed loop. base_lines = VGroup( *[ Line(corners[i], corners[(i + 1) % len(corners)], color=BLUE) for i in range(len(corners)) ] ) # Create the side edges from each corner to the apex. side_lines = VGroup( *[Line(corner, apex, color=GREEN) for corner in corners] ) return VGroup(base_lines, side_lines) # Create an always_redraw mobject so that whenever height_tracker changes, # the pyramid is redrawn with the new apex position. pyramid = always_redraw(lambda: get_pyramid(height_tracker.get_value())) # Transition from the static square (at height 0) into our pyramid object. # (At height=0, the side edges have zero length so the drawing looks identical to the square.) self.play(ReplacementTransform(square, pyramid), run_time=1) self.wait(0.5) # Animate the pyramid “lifting” by increasing the tracked height. self.play(height_tracker.animate.set_value(2), run_time=3) self.wait(1) # Now animate the pyramid “shrinking” back into a square by lowering the apex. self.play(height_tracker.animate.set_value(0), run_time=3) self.wait(1) # Optionally, perform a slight camera move to show off the 3D nature. self.move_camera(phi=75 * DEGREES, theta=-30 * DEGREES, run_time=2) self.wait(1)
Here's the output of the program:
Here, this model really struggled with the 3D projection and failed to transform the square into a pyramid.
Final Verdict: The Claude 3.7 Sonnet and Grok 3 models got it completely correct, but in terms of animation, I prefer the output from the Grok 3 model ✅. o3-mini-high failed completely and couldn't even reach the solution.
Conclusion
It's fair to say that Claude 3.7 is exactly what it claims to be. In all five questions we compared, it was the clear winner almost every time.
Now is no time to wait for luck. Imagine an AI model building stuffs in no time with 62.3% accuracy. Start building stuffs and improving your coding skills, or get ready to be replaced by AI (probably 🤷🏼♂️).
It doesn't necessarily mean that Claude 3.7 is the answer to everything, and there will be a time when other AI models beat this model's benchmarks.
The race between the AI models will never stop, and the game's always on!
What do you think? Let me know your thoughts in the comments below! 👇🏻