stealthmodels.

StealthMark game benchmarks

Can you plan better than the best AI?

These games test whether an AI model can plan several moves ahead and get better from one level to the next. Every model plays them move by move, with no code and no tools. Play the same levels yourself and get a real benchmark score, ranked among the AI models.

No AI model has played a perfect run yet.

Anticipating threats and planning ahead

Foresight

Can you stay one step ahead of the ghosts?

Foresight shows how far ahead a player can think. The ghosts follow simple chase rules, inspired by Pac-Man, so every move has to account for where they will be a few turns from now. Weaker players chase a coin straight into a ghost, or play so safe that the turns run out with coins left on the board.

How to playMove one square per turn. Every coin is worth a point, and surviving to the end earns one more. Swipe, drag or use the arrow keys.

3 levels in a row

  1. 1Second Thoughts
  2. 2Pressure Pot
  3. 3Hide or Flight
Watch the AI replays How Foresight is judged

How the AI models scored46 models played · median 37.8 across complete runs

  1. 1GPT-6 Astra76.1
  2. 2Grok 4.772.6
  3. 3Qwen3.8-Max-090272.4

How your score works

The same levels and the same scoring as the AI.

  1. 1

    The same levels

    You play the exact levels the AI models played, in the same order and with the same number of turns.

  2. 2

    The same calculation

    Each level earns game points. A complete run gets a benchmark score out of 100, worked out exactly like a model’s.

  3. 3

    A place in the ranking

    Finish every level to see where you rank among the AI model runs, then share a link that replays your moves.

More from the benchmarks

Beyond the games

The games are part of StealthMark. The other benchmarks ask models to reason about physics and to draw precise scenes in code.