[HN Gopher] Show HN: TetrisBench - Gemini Flash reaches 66% win ...
___________________________________________________________________
Show HN: TetrisBench - Gemini Flash reaches 66% win rate on Tetris
against Opus
Author : ykhli
Score : 55 points
Date : 2026-01-26 18:42 UTC (4 hours ago)
(HTM) web link (tetrisbench.com)
(TXT) w3m dump (tetrisbench.com)
| akomtu wrote:
| It would be more interesting to make it build a chess engine and
| compare it against Stockfish. The chess engine should be a
| standalone no-dependencies C/C++ program that fits in NNN lines
| of code.
| gpm wrote:
| Comparing against stockfish isn't fair. That's comparing
| against enormous amounts of compute spent experimenting with
| strategies, training neutral nets, etc.
|
| It will lose so badly there will be no point in the comparison.
|
| Besides you could compare models (and harnesses) directly
| against eachother.
| vunderba wrote:
| My back-of-the-envelope guess would be that 99% of LLMs given
| the task to build a chess engine would probably just end up
| implementing a flavor of negamax and calling it a day.
|
| https://en.wikipedia.org/wiki/Negamax
| OGEnthusiast wrote:
| Gemini 3 Flash is at a very nice point along the price-
| performance curve. A good workhorse model, while supplementing it
| with Opus 4.5 / Gemini 3 Pro for more complex tasks.
| bubblesorting wrote:
| Very cool! I am a good Tetris player (in the top 10% of players)
| and wanted to give brick yeeting against an LLM a spin.
|
| Some feedback: - Knowing the scoring system is helpful when going
| 1v1 high score
|
| - Use a different randomization system, I kept getting starved
| for pieces like I. True random is fine, throwing a copy of every
| piece into a bag and then drawing them one by one is better (7
| bag), nearly random with some lookbehind to prevent getting a
| string of ZSZS is solid, too (TGM randomizer)
|
| - Piece rotation feels left-biased, and keeps making me mis-drop,
| like the T pieces shift to the left if you spin 4 times. Check
| out https://tetris.wiki/images/thumb/3/3d/SRS-
| pieces.png/300px-S... or
| https://tetris.wiki/images/b/b5/Tgm_basic_ars_description.pn...
| for examples of how other games are doing it.
|
| - Clockwise and counter-clockwise rotation is important for human
| players, we can only hit so many keys per second
|
| - re-mappable keys are also appreciated
|
| Nice work, I'm going to keep watching.
| qsort wrote:
| The worst thing is that the delayed auto shift is slightly off
| and it messes my finesse. (I used to play competitive tetris as
| well, but between getting older -> worse reflexes and vision
| problems I can't really play anymore. Weirdly, finesse muscle
| memory is still working.)
|
| I don't think the goal is to make a PvP simulator, it would be
| too easy to cheese or do weird strategies. It's mostly for LLMs
| to play.
| bubblesorting wrote:
| Hello fellow Tetris nerd with a -sort username :)
|
| On the topic of reflexes decaying (I'm getting there, in my
| late 30s): Have you played Stackflow? It's a number go up
| roguelite disguised as an arcade brick stacking game, but the
| gravity is low enough that it is effectively turn based. More
| about 'deck' building, less about chaining PCs and C-Spins.
| vunderba wrote:
| I actually grew up playing the Spectrum HoloByte version of
| Tetris for PC, which only lets you rotate in one direction. As
| a result, I ended up playing NES Tetris for years as a kid
| before realizing it lets you rotate clockwise /
| counterclockwise!
|
| https://en.wikipedia.org/wiki/Tetris_(Spectrum_HoloByte)
| arendtio wrote:
| There are some concepts clashing here.
|
| I mean, if you let the LLM build a testris bot, it would be 1000x
| better than what the LLMs are doing. So yes, it is fun to win
| against an AI, but to be fair against such processing power, you
| should not be able to win. It is only possible because LLMs are
| not built for such tasks.
| i_cannot_hack wrote:
| Fun fact: Humans were not build for playing Tetris either!
| westurner wrote:
| Task: play tetris
|
| Task: write and optimize a tetris bot
|
| Task: write and safely online optimize a tetris bot with
| consideration for cost to converge
|
| openai/baselines (7 years ago) was leading on RL and then
| AlphaZero and Self-Attention Transformer networks.
|
| LLMs are trained with RL, but aren't general purpose game
| theoretic RL agents?
| burkaman wrote:
| It's actually 80% against Opus, 66% average against the 5 models
| it's tested with.
| esafak wrote:
| I imagine this is because Tetris is visual and the Gemini models
| are strong visually.
| bogtog wrote:
| I figure OP would try and give the models pure text forms of
| the game?
|
| .....
|
| l....
|
| l....
|
| l.ttt
|
| l..t.
| vunderba wrote:
| Interesting but frustratingly vague on details. How exactly are
| the models playing? Is it using some kind of PGN equivalent in
| Tetris that represents a on-going game, passing an ASCII
| representation, encoding as a JSON structure, or just directly
| sending screenshots of the game to the various LLMs?
| storystarling wrote:
| It has to be turn-based. Even with Flash's speed, the inference
| latency would kill you in a real-time loop. They're likely
| pausing the game state after every tick to wait for the API
| response before resuming.
| ykhli wrote:
| answered this in a comment above! It's not turn or visual
| layout based since LLMs are not trained that way. The
| representation is a JSON structure, but LLMs plug in algorithms
| and keeps optimizing it as the game state evolves
| vunderba wrote:
| Thanks for the clarification! Kind of reminds me of the Brian
| Moore's AI clocks which uses several LLMs to continuously
| generate HTML/CSS to create an analog clock for comparisons.
|
| https://clocks.brianmoore.com
| tiahura wrote:
| I'd like to see a nethackbench.
| ykhli wrote:
| Thanks for all the questions! More details on how this works:
|
| - Each model starts with an initial optimization function for
| evaluating Tetris moves.
|
| - As the game progresses, the model sees the current board state
| and updates its algorithm--adapting its strategy based on how the
| game is evolving.
|
| - The model continuously refines its optimizer. It decides when
| it needs to re-evaluate and when it should implement the next
| optimization function
|
| - The model generates updated code, executes it to score all
| placements, and picks the best move.
|
| - The reason I reframed this problem to a coding problem is
| Tetris is an optimization game in nature. At first I did try
| asking LLMs where to place each piece at every turn but models
| are just terrible at visual reasoning. What LLMs great at though
| is coding.
| p0w3n3d wrote:
| Guys, I don't know how to tell you but... Tetris can web solved
| without LLM...
| purplecats wrote:
| watch link?
| segmondy wrote:
| ... and what does this prove? what can you decide to use one LLM
| to solve over another based on this tetrisbench besides play
| tetris?
| indigodaddy wrote:
| Is there a tl;dr on why this is? Does it just make faster
| decisions?
| bityard wrote:
| Looks fun, but I'm not willing to give out my email address just
| to play a game.
|
| Also, if the creator is reading this, you should know that Tetris
| Holdings is extremely aggressive with their trademark
| enforcement.
___________________________________________________________________
(page generated 2026-01-26 23:00 UTC)