Building a Rubik's Cube Decision Arena with 6 Decision Models (Laya, Clef, GLiNER 2.5, Kev and Strands Decider)

What happens when six small AI models — four of them running on a laptop — are asked to solve the same scrambled cube, one move at a time?

Most "AI plays a game" demos hide the interesting part. They show a model winning, and you are left to guess how much of that was the model and how much was the harness. This project does the opposite: it puts six models in a glass box, gives them the exact same scrambled Rubik's cube, the exact same question every turn, and shows you — live, in one screen — exactly where each one succeeds and where it falls apart.

The result is uncomfortable and honest. A Rubik's cube is a planning problem: you need lookahead and search. The models in this arena are decision models: fast, calibrated judgments about the current state. They are not the same thing, and the arena makes that difference visible.

1. The premise: decision models vs. planning

A "decision model" (sometimes called a system-one model) does one thing well: it looks at a situation, weighs a closed set of options, and returns a choice with a confidence. It is fast and it is often surprisingly well-calibrated.

A Rubik's cube is not a decision problem. It is a search problem. From a scrambled state there is an optimal solution length, and finding it means exploring a tree of moves. A model that only ever looks at the current state — with no memory of the plan and no lookahead — is being asked to do something it was not built for.

So the arena asks a precise question:

Given the same cube and the same one-move question, how good are six real decision models at picking moves that actually help?

Everything else in the project exists to answer that question fairly.

2. The two hard rules

The whole comparison is only meaningful if the conditions are identical, so the code enforces two rules everywhere:

1. Every engine gets the identical state and the identical question. No engine gets extra context, a better prompt, retries, or a second look. Same 54 stickers, same 18 options, same instructions.
2. Nothing is ever faked. If a model or its server is missing, its panel reads unavailable with the exact reason, and the race simply runs without it. There are no placeholder scores and no synthetic results.

That second rule sounds obvious until you build a demo. It is very tempting to fill a dead panel with something plausible. The arena refuses.

3. Architecture

 ┌──────────────────────────────────┐ │ browser http://127.0.0.1:8077 │ │ ui/index.html (CSS-3D cubes) │ └───────────────┬──────────────────┘ GET / GET /api/engines │ POST /api/run GET /api/run/<id> GET /api/chart/<id> │ ┌───────────────▼──────────────────┐ │ server.py (stdlib HTTP) │ │ Hub: loaded engines + active run │ │ CHART_LOCK serialises matplotlib │ └───────┬───────────────────┬───────┘ │ │ one thread per engine (run in parallel) │ ▼ ▼ ┌────────────────────┐ ┌─────────────────────────────┐ │ arena.run() │ │ charts.build_scorecard() │ │ guided | greedy │ │ -> results/chart_<id>.png │ │ | staged │ │ progress · latency · │ └─────────┬──────────┘ │ guided · final │ │ └─────────────────────────────┘ each turn: decide(state, question) ▼ ┌────────────────────────────────────────────────────────────────┐ │ engines.py — one contract, six adapters │ │ laya MLX, in-process gliner CPU, in-process │ │ strands HTTP 127.0.0.1:8010 kev HTTP 127.0.0.1:8008 │ clef / clef-flash Cloudflare Workers AI (HTTPS) │ └────────────────────────────────────────────────────────────────┘ │ ▼ ┌────────────────────────────────────────────────────────────────┐ │ cube.py (pycuber state + metrics) │ │ solver.py (kociemba plan / first move) │ └────────────────────────────────────────────────────────────────┘ 

The stack is deliberately boring: a stdlib HTTP server, a single HTML file, and plain Python. There is no framework, no bundler, and no build step. You can read the whole thing in an afternoon.

Tech stack

4. The cube model

Everything starts with a deterministic scramble. Given a seed, every engine sees the same cube — and the same cube every time you rerun the demo.

# cube.py FACES = "URFDLB" MOVES = [f + s for f in FACES for s in ("", "'", "2")] # 18 quarter/half turns  def scramble(seed: int, n: int = 25) -> tuple[Cube, list[str]]: rng = random.Random(seed) seq: list[str] = [] prev_face = None while len(seq) < n: mv = rng.choice(MOVES) if mv[0] == prev_face: # avoid trivial same-face repeats  continue prev_face = mv[0] seq.append(mv) c = Cube() for mv in seq: c.perform_algo(mv) return c, seq 

Two metrics are tracked. A sticker is correct when it matches its own face's centre colour (centres never move, so the centre is the solved colour). That gives a smooth 0–54 progress line; complete faces give a chunky 0–6 milestone.

# cube.py def solved_facelets(cube: Cube) -> int: n = 0 for f in FACES: ctr = centre_colour(cube, f) face = _face(cube, f) for r in range(3): for c in range(3): if face[r][c].colour == ctr: n += 1 return n 

The model never sees a Cube object. It sees a compact text state, identical for every engine:

# cube.py def state_text(cube: Cube) -> str: rows = facelet_rows(cube) body = "\n".join(f"{f}: {rows[f]}" for f in FACES) return ( "3x3 Rubik's cube. Faces U R F D L B, each 9 stickers read row by row " "seen from outside. Letters are sticker colours (W Y G B R O). A face is " "solved when all 9 stickers match its fixed centre sticker.\n" f"{body}\n" f"Correct stickers: {solved_facelets(cube)}/54. " f"Complete faces: {solved_faces(cube)}/6." ) 

5. The solver bridge (and its encoding trap)

Guided mode needs an optimal-ish solver. The project uses kociemba, but wiring it up has a classic gotcha: pycuber colours its stickers with colour names, and Kociemba wants a 54-character string of face letters in URFDLB order.

Hardcoding the colour→face map is wrong, because pycuber's default cube is not the usual white-up arrangement. The fix is to read the map off the centres, which never move:

# solver.py FACES = "URFDLB" def colour_map(cube: Cube) -> dict[str, str]: """colour name -> face letter, taken from the fixed centres.""" return {cube.get_face(f)[1][1].colour: f for f in FACES} def facelet_string(cube: Cube) -> str: """54-char Kociemba facelet string, URFDLB order, row-major from outside.""" m = colour_map(cube) out: list[str] = [] for f in FACES: face = cube.get_face(f) for r in range(3): for c in range(3): out.append(m[face[r][c].colour]) return "".join(out) @lru_cache(maxsize=200_000) def _solve_cached(state: str) -> str: return kociemba.solve(state) 

Every state is cached by its facelet string. The race revisits states constantly (neutral moves, repeated positions), and Kociemba is by far the slowest part of the loop — the cache is the difference between a snappy demo and a stall.

Two more things worth knowing if you build on this:

• kociemba has no Apple-silicon wheel, so it always compiles a small C extension. If that build fails, the module degrades cleanly: greedy and staged modes still work, and guided mode says exactly what is missing.
• The solver's solution length is near-optimal, not provably optimal. That is why guided runs take optimal + a few moves rather than exactly optimal.

6. One contract, six engines

This is the heart of the project. Six very different runtimes — an in-process MLX model, a torch server, a CPU classifier, two cloud endpoints, and a local OpenAI-ish server — are all reduced to one method:

# engines.py def decide(self, state: str, question: dict, qid: str = "move") -> Decision: ... @dataclass class Decision: engine: str choice: str # e.g. "R2"  confidence: float | None probabilities: dict[str, float] # over the 18 moves (may be empty)  latency_ms: float error: str | None = None 

The question is a closed choice over the 18 legal moves, with a description for each — the shape that strands-decider requires, and that the others accept too:

# engines.py _FACE_NAME = {"U": "up", "R": "right", "F": "front", "D": "down", "L": "left", "B": "back"} MOVE_CRITERIA = {} for _f, _n in _FACE_NAME.items(): MOVE_CRITERIA[_f] = f"turn the {_n} face clockwise 90 degrees" MOVE_CRITERIA[_f + "'"] = f"turn the {_n} face anticlockwise 90 degrees" MOVE_CRITERIA[_f + "2"] = f"turn the {_n} face 180 degrees" def move_question(instructions: str) -> dict: return {"type": "choice", "instructions": instructions, "criteria": dict(MOVE_CRITERIA)} 

Most engines share an HTTP transport, so adding one is usually a tiny subclass:

# engines.py class HttpEngine(Engine): def probe(self) -> tuple[bool, str | None]: """A dead server must read as unavailable, not as 'ready'.""" if not self.health_url: return True, None try: r = httpx.get(self.health_url, timeout=3.0) except Exception as e: return False, f"no server at {self.health_url} ({type(e).__name__})" return True, None def decide(self, state, question, qid="move") -> Decision: body = {"state": state, "model": self.model, "questions": {qid: question}} t0 = time.perf_counter() try: r = self.client.post(self.url, json=body) r.raise_for_status() resp = r.json() except Exception as e: return Decision(self.name, "", None, latency_ms=(time.perf_counter() - t0) * 1000, error=f"{type(e).__name__}: {e}") dt = (time.perf_counter() - t0) * 1000 choice, conf, probs = _parse_answers(resp, qid) return Decision(self.name, choice, conf, probs, dt) 

The probe() method is why a dead Kev server shows unavailable: no server at 127.0.0.1:8008 instead of silently reporting "ready" and failing on every move.

The six models

Why two run in the cloud: this was built on an Apple M2 mini with 8 GB of RAM. A 27B model does not fit at any quantization, so Clef and Clef-Flash are called on Workers AI where they cost no local RAM. The other four run locally — including on a 16 GB laptop — which is the point of the demo.

7. The guided loop: the solver plans, the model decides

The unaided models cannot solve a cube. That is measured, not assumed: after 24 moves each, three different architectures all landed on exactly the sticker count they started from. So guided mode separates the two jobs cleanly — the solver is the search, the model is the decision layer inside it.

# arena.py (abridged) plan = solution(cube) # a concrete, known-good move list correct = plan[0] # the solver's optimal next move  d = engine.decide(state_text(cube), move_question(GREEDY_Q)) mv = pick_move(d, policy, rng) # sample the distribution, or take argmax  play, tag, replan = correct, "corrected", False if mv == correct: tag = "hit" # matched the solver exactly elif mv in MOVES: probe = cube.copy(); apply_move(probe, mv) d_m = len(solution(probe)) if d_m < len(plan): play, tag, replan = mv, "accepted", True # a different move that helped  elif d_m == len(plan) and neutral_budget > 0: play, tag, replan = mv, "neutral", True # wasted turn (budgeted)  neutral_budget -= 1 else: play, tag = correct, "corrected" # solver overrides else: play, tag = correct, "corrected" # unusable answer  apply_move(cube, play) plan = solution(cube) if replan else plan[1:] 

The model gets the same 18-move question as the unaided race, so the two are directly comparable. Each pick is scored:

The cube is guaranteed to advance because the solver always holds a valid plan, and after the neutral budget is spent every move must strictly reduce the distance.

But here is the subtlety that trips people up: a corrected turn still costs one of the moves you allocated. The solver is doing the solving, and the model is being measured — but the clock runs on every turn, including the ones where the model was overruled. With an optimal distance of 22 and a neutral budget of 6, a guided run can legitimately need up to 28 moves. Set the cap below that and slower models get cut off unsolved while still showing the done status.

Policy: how a distribution becomes a move

Most of these models return a probability for each of the 18 moves. Policy decides what to do with it:

# arena.py def pick_move(d, policy: str, rng: random.Random) -> str: if policy == "sample" and d.probabilities: opts = [(m, v) for m, v in d.probabilities.items() if m in MOVES and v > 0] if opts: total = sum(v for _, v in opts) r = rng.random() * total acc = 0.0 for m, v in opts: acc += v if r <= acc: return m return opts[-1][0] return d.choice # argmax 

• sample draws the move from the model's own distribution. This is the honest way to run a decision model in a loop, and it prevents the collapse you get from always taking the top choice.
• argmax always takes the most likely move. In practice it collapses — the model repeats one move forever — so it is shown mainly for contrast.

8. The server: threads, polling, and a chart race

The server is stdlib-only. Its job is small: hold the loaded engines, run one race at a time, and serve the UI. The interesting part is concurrency.

A run spawns one thread per ready engine, so all six models think in parallel:

# server.py def _drive(self, run: dict) -> None: threads = [] for panel in run["panels"]: if panel["status"] != "ready": continue t = threading.Thread(target=self._one_engine, args=(run, panel), daemon=True) t.start() threads.append(t) for t in threads: t.join() # ... persist the run + render the chart, THEN flip status to "done" 

Every turn, the engine thread fires an on_move callback that updates the shared panel under a lock. The browser polls /api/run/<id> every 350 ms and redraws the cubes.

There is one nasty bug worth calling out, because it is the kind of thing that only shows up in a demo: matplotlib's pyplot is not thread-safe. The scorecard is built on the run thread when a race finishes, and on demand by the /api/chart/<id> route. If those two ever overlap, the render corrupts and the browser shows a broken image.

The fix is two-fold — a lock, and getting the order right:

# server.py CHART_LOCK = threading.Lock() # ... in _drive(), after all engine threads join: snapshot = {**run, "status": "done", "finished_at": finished_at} (RESULTS / f"ui_run_{run['id']}.json").write_text(json.dumps(snapshot, indent=2)) with CHART_LOCK: build_scorecard(run, RESULTS / f"chart_{run['id']}.png") with self.lock: run["status"Source：https://dev.to/harishkotra/building-a-rubiks-cube-decision-arena-with-6-decision-models-laya-clef-gliner-25-kev-and-2l9i
My favorites

Related posts

FiveM Script Database Migrations: What to Check Before You Install

Most FiveM script problems that show up a week after the install are not script bugs. They are database problems, and th

0dev.to

The insurance edge case that breaks event-driven policy pipelines

If you're moving insurance policy data from a nightly batch to an event stream, the broker is the easy part. The hard pa

0dev.to

The fix for an empty state isn't filling it

Last week I posted on Indie Hackers about a decision in my renovation cost tool: it ships with an empty price book. The

0dev.to UX

Five Things That Make Dependabot Painful for Terraform

A Terraform block in dependabot.yml looks identical to an npm or uv one: - package-ecosystem : terraform directory : /te

0dev.to GitHub

Tracking Roblox player counts: what the public data actually gives you

Roblox does not publish a public API for per-game concurrent player counts, so anything you see is a sample. I have been

0dev.to Data

Telegram gold signals this week: results to Oct 30

From October 24 to October 30, we executed 3,629 signals from 405 Telegram gold channels at the broker. More channels ma

0dev.to Data