{"id":10479,"date":"2026-01-05T22:02:25","date_gmt":"2026-01-05T22:02:25","guid":{"rendered":"https:\/\/techtrendfeed.com\/?p=10479"},"modified":"2026-01-05T22:02:25","modified_gmt":"2026-01-05T22:02:25","slug":"i-requested-chatgpt-claude-and-deepseek-to-construct-tetris","status":"publish","type":"post","link":"https:\/\/techtrendfeed.com\/?p=10479","title":{"rendered":"I Requested ChatGPT, Claude and DeepSeek to Construct Tetris"},"content":{"rendered":"

\n<\/p>\n

\n

$\"I$ $\"I$
Picture by Creator<\/span><\/center>
\n\u00a0<\/p>\n

#\u00a0<\/span>Introduction<\/h2>\n
\u00a0
It looks like virtually each week, a brand new mannequin claims to be state-of-the-art, beating current AI fashions on all benchmarks.<\/p>\n
I get free entry to the most recent AI fashions at my full-time job inside weeks of launch. I usually don\u2019t pay a lot consideration to the hype and simply use whichever mannequin is auto-selected by the system.<\/p>\n
Nonetheless, I do know builders and associates who need to construct software program with AI that may be shipped to manufacturing. Since these initiatives are self-funded, their problem lies find one of the best mannequin to do the job. They need to steadiness value with reliability.<\/p>\n
Because of this, after the discharge of GPT-5.2, I made a decision to run a sensible take a look at to grasp whether or not this mannequin was definitely worth the hype, and if it actually was higher than the competitors. <\/p>\n
Particularly, I selected to check flagship fashions from every supplier: Claude Opus 4.5<\/strong> (Anthropic\u2019s most succesful mannequin), GPT-5.2 Professional<\/strong> (OpenAI\u2019s newest prolonged reasoning mannequin), and DeepSeek V3.2<\/strong> (one of many newest open-source options).<\/p>\n
To place these fashions to the take a look at, I selected to get them to construct a playable Tetris sport with a single immediate.<\/p>\n
These have been the metrics I used to guage the success of every mannequin:<\/p>\n
\u00a0<\/p>\n\n\n\n\n\n\n\n\n
Standards<\/th>\n Description<\/th>\n<\/tr>\n<\/thead>\n
First Try Success<\/strong><\/td>\n With only one immediate, did the mannequin ship working code? A number of debugging iterations results in larger value over time, which is why this metric was chosen.<\/td>\n<\/tr>\n
Function Completeness<\/strong><\/td>\n Had been all of the options talked about within the immediate constructed by the mannequin, or was something missed out?<\/td>\n<\/tr>\n
Playability<\/strong><\/td>\n Past the technical implementation, was the sport truly easy to play? Or have been there points that created friction within the consumer expertise?<\/td>\n<\/tr>\n
Price-effectiveness<\/strong><\/td>\n How a lot did it value to get production-ready code?<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\u00a0<\/p>\n
#\u00a0<\/span>The Immediate<\/h2>\n
\u00a0
Right here is the immediate I entered into every AI mannequin:<\/p>\n
\n
\nConstruct a totally purposeful Tetris sport as a single HTML file that I can open straight in my browser.<\/p>\n
Necessities:<\/p>\n
GAME MECHANICS:
– All 7 Tetris piece varieties
– Easy piece rotation with wall kick collision detection
– Items ought to fall mechanically, enhance the velocity step by step because the consumer’s rating will increase
– Line clearing with visible animation
– “Subsequent piece” preview field
– Sport over detection when items attain the highest<\/p>\n
CONTROLS:
– Arrow keys: Left\/Proper to maneuver, All the way down to drop quicker, As much as rotate
– Contact controls for cell: Swipe left\/proper to maneuver, swipe all the way down to drop, faucet to rotate
– Spacebar to pause\/unpause
– Enter key to restart after sport over<\/p>\n
VISUAL DESIGN:
– Gradient colours for every bit kind
– Easy animations when items transfer and contours clear
– Clear UI with rounded corners
– Replace scores in actual time
– Degree indicator
– Sport over display screen with last rating and restart button<\/p>\n
GAMEPLAY EXPERIENCE AND POLISH:
– Easy 60fps gameplay
– Particle results when strains are cleared (non-compulsory however spectacular)
– Improve the rating based mostly on variety of strains cleared concurrently
– Grid background
– Responsive design<\/p>\n
Make it visually polished and really feel satisfying to play. The code ought to be clear and well-organized.\n<\/p>\n<\/blockquote>\n
\u00a0<\/p>\n
\u00a0<\/p>\n
#\u00a0<\/span>The Outcomes<\/h2>\n
\u00a0<\/p>\n
\/\/\u00a0<\/span>1. Claude Opus 4.5<\/h4>\n
The Opus 4.5 mannequin constructed precisely what I requested for. <\/p>\n
The UI was clear and directions have been displayed clearly on the display screen. All of the controls have been responsive and the sport was enjoyable to play. <\/p>\n
The gameplay was so easy that I truly ended up enjoying for fairly a while and obtained sidetracked from testing the opposite fashions.<\/p>\n
Additionally, Opus 4.5 took lower than 2 minutes to supply me with this working sport, leaving me impressed on the primary attempt.<\/p>\n
\u00a0<\/p>\n
$\"Tetris$ $\"Tetris$
Tetris sport constructed by Opus 4.5<\/span><\/center>
\n\u00a0<\/p>\n
\/\/\u00a0<\/span>2. GPT-5.2 Professional<\/h4>\n
GPT-5.2 Professional is OpenAI\u2019s newest mannequin with prolonged reasoning. For context, GPT-5.2 has three tiers: Instantaneous, Pondering, and Professional. On the level of writing this text, GPT-5.2 Professional is their most clever mannequin, offering prolonged pondering and reasoning capabilities.<\/p>\n
Additionally it is 4x costlier than Opus 4.5.<\/p>\n
There was a variety of hype round this mannequin, main me to go in with excessive expectations.<\/p>\n
Sadly, I used to be underwhelmed by the sport this mannequin produced.<\/p>\n
On the first attempt, GPT-5.2 Professional produced a Tetris sport with a format bug. The underside rows of the sport have been exterior of the viewport, and I couldn\u2019t see the place the items have been touchdown.<\/p>\n
This made the sport unplayable, as proven within the screenshot beneath:<\/p>\n
\u00a0<\/p>\n
$\"Tetris$ $\"Tetris$
Tetris sport constructed by GPT-5.2<\/span><\/center>
\n\u00a0<\/p>\n
I used to be particularly shocked by this bug because it took round 6 minutes for the mannequin to provide this code.<\/p>\n
I made a decision to attempt once more with this follow-up immediate to repair the viewport downside:<\/p>\n
\n
The sport works, however there is a bug. The underside rows of the Tetris board are reduce off on the backside of the display screen. I am unable to see the items after they land and the canvas extends past the seen viewport.<\/p>\n
Please repair this by:
1. Ensuring your complete sport board suits within the viewport
2. Including correct centering so the complete board is seen<\/p>\n
The sport ought to match on the display screen with all rows seen.<\/p>\n<\/blockquote>\n
\u00a0<\/p>\n
After the follow-up immediate, the GPT-5.2 Professional mannequin produced a purposeful sport, as seen within the beneath screenshot:<\/p>\n
\u00a0<\/p>\n
$\"Tetris$ $\"Tetris$
Tetris second attempt by GPT-5.2<\/span><\/center>
\n\u00a0<\/p>\n
Nonetheless, the sport play wasn\u2019t as easy because the one produced by the Opus 4.5 mannequin. <\/p>\n
After I pressed the \u201cdown\u201d arrow for the piece to drop, the subsequent piece would generally plummet immediately at a excessive velocity, not giving me sufficient time to consider the right way to place it.<\/p>\n
The sport ended up being playable provided that I let every bit fall by itself, which wasn\u2019t one of the best expertise.<\/p>\n
(Be aware: I attempted the GPT-5.2 Normal mannequin too, which produced related buggy code on the primary attempt.)<\/p>\n
\u00a0<\/p>\n
\/\/\u00a0<\/span>3. DeepSeek V3.2<\/h4>\n
DeepSeek\u2019s first try at constructing this sport had two points:<\/p>\n
\n
Items began disappearing after they hit the underside of the display screen.\n<\/li>\n
The \u201cdown\u201d arrow that\u2019s used to drop the items quicker ended up scrolling your complete webpage slightly than simply shifting the sport items.\n<\/li>\n<\/ul>\n
\u00a0<\/p>\n
$\"Tetris$ $\"Tetris$
Tetris sport constructed by DeepSeek V3.2<\/span><\/center>
\n\u00a0<\/p>\n
I re-prompted the mannequin to repair this situation, and the gameplay controls ended up working appropriately. <\/p>\n
Nonetheless, some items nonetheless disappeared earlier than they landed. This made the sport utterly unplayable even after the second iteration.<\/p>\n
I\u2019m positive that this situation may be mounted with 2\u20133 extra prompts, and given DeepSeek\u2019s low pricing, you might afford 10+ debugging rounds and nonetheless spend lower than one profitable Opus 4.5 try.<\/p>\n
\u00a0<\/p>\n
#\u00a0<\/span>Abstract: GPT-5.2 vs Opus 4.5 vs DeepSeek 3.2<\/h2>\n
\u00a0<\/p>\n
\/\/\u00a0<\/span>Price Breakdown<\/h4>\n
Here’s a value comparability between the three fashions:
\u00a0<\/p>\n\n\n\n\n\n\n\n\n
Mannequin<\/th>\n Enter (per 1M tokens)<\/th>\n Output (per 1M tokens)<\/th>\n<\/tr>\n<\/thead>\n
DeepSeek V3.2<\/strong><\/td>\n $0.27<\/td>\n $1.10<\/td>\n<\/tr>\n
GPT-5.2<\/strong><\/td>\n $1.75<\/td>\n $14.00<\/td>\n<\/tr>\n
Claude Opus 4.5<\/strong><\/td>\n $5.00<\/td>\n $25.00<\/td>\n<\/tr>\n
GPT-5.2 Professional<\/strong><\/td>\n $21.00<\/td>\n $84.00<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\u00a0<\/p>\n
DeepSeek V3.2 is the most affordable different, and you too can obtain the mannequin\u2019s weights totally free and run it by yourself infrastructure.<\/p>\n
GPT-5.2 is sort of 7x costlier than DeepSeek V3.2, adopted by Opus 4.5 and GPT-5.2 Professional.<\/p>\n
For this particular activity (constructing a Tetris sport), we consumed roughly 1,000 enter tokens and three,500 output tokens. <\/p>\n
For every further iteration, we are going to estimate an additional 1,500 tokens per further spherical. Right here is the overall value incurred per mannequin:<\/p>\n
\u00a0<\/p>\n\n\n\n\n\n\n\n\n
Mannequin<\/th>\n Complete Price<\/th>\n End result<\/th>\n<\/tr>\n<\/thead>\n
DeepSeek V3.2<\/strong><\/td>\n ~$0.005<\/td>\n Sport is not playable<\/td>\n<\/tr>\n
GPT-5.2<\/strong><\/td>\n ~$0.07<\/td>\n Playable, however poor consumer expertise<\/td>\n<\/tr>\n
Claude Opus 4.5<\/strong><\/td>\n ~$0.09<\/td>\n Playable and good consumer expertise<\/td>\n<\/tr>\n
GPT-5.2 Professional<\/strong><\/td>\n ~$0.41<\/td>\n Playable, however poor consumer expertise<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\u00a0<\/p>\n
#\u00a0<\/span>Takeaways<\/h2>\n
\u00a0
Primarily based on my expertise constructing this sport, I might persist with the Opus 4.5 mannequin for daily coding duties<\/strong>. <\/p>\n
Though GPT-5.2 is cheaper than Opus 4.5, I personally wouldn’t use it to code, for the reason that iterations required to yield the identical outcome would probably result in the identical sum of money spent.<\/p>\n
DeepSeek V3.2, nevertheless, is much extra reasonably priced than the opposite fashions on this record. <\/p>\n
For those who\u2019re a developer on a funds and have time to spare on debugging, you’ll nonetheless find yourself saving cash even when it takes you over 10 tries to get working code.<\/p>\n
I used to be shocked at GPT 5.2 Professional\u2019s incapacity to provide a working sport on the primary attempt, because it took round 6 minutes to assume earlier than arising with flawed code. In spite of everything, that is OpenAI\u2019s flagship mannequin, and Tetris ought to be a comparatively easy activity.<\/p>\n
Nonetheless, GPT-5.2 Professional\u2019s strengths lie in math and scientific analysis, and it’s particularly designed for issues that don\u2019t depend on sample recognition from coaching knowledge. Maybe this mannequin is over-engineered for easy day-to-day coding duties, and will as an alternative be used when constructing one thing that’s complicated and requires novel structure.<\/p>\n
The sensible takeaway from this experiment:<\/p>\n
\n
Opus 4.5 performs finest at day-to-day coding duties.\n<\/li>\n
DeepSeek V3.2 is a funds different that delivers cheap output, though it requires some debugging effort to achieve your required consequence.\n<\/li>\n
GPT-5.2 (Normal) didn\u2019t carry out in addition to Opus 4.5, whereas GPT-5.2 (Professional) might be higher suited to complicated reasoning than fast coding duties like this one.\n<\/li>\n<\/ul>\n
Be at liberty to duplicate this take a look at with the immediate I\u2019ve shared above, and pleased coding!
&nbsp
&nbsp<\/p>\n
Natassha Selvaraj<\/a><\/strong><\/a> is a self-taught knowledge scientist with a ardour for writing. Natassha writes on every little thing knowledge science-related, a real grasp of all knowledge matters. You may join along with her on LinkedIn<\/a> or try her YouTube channel<\/a>.<\/p>\n<\/p><\/div>\n\n","protected":false},"excerpt":{"rendered":"
Picture by Creator \u00a0 #\u00a0Introduction \u00a0It looks like virtually each week, a brand new mannequin claims to be state-of-the-art, beating current AI fashions on all benchmarks. I get free entry to the most recent AI fashions at my full-time job inside weeks of launch. I usually don\u2019t pay a lot consideration to the hype and […]<\/p>\n","protected":false},"author":2,"featured_media":10481,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[7143,73,1175,458,459,7268],"class_list":["post-10479","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-asked","tag-build","tag-chatgpt","tag-claude","tag-deepseek","tag-tetris"],"_links":{"self":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/10479","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=10479"}],"version-history":[{"count":1,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/10479\/revisions"}],"predecessor-version":[{"id":10480,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/10479\/revisions\/10480"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/media\/10481"}],"wp:attachment":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=10479"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=10479"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=10479"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}