GameBench OPEN BENCHMARK
build · level 1 · Benchmark 0.1.2

2048

2048 · build.2048.v1

1.0.0task version
9atomic tests
60m agent budget
0published runs
Generated outputs

Every seed stays visible.

Official output defaults to seed 104729. The gallery never chooses the highest-scoring attempt, and failures remain in the record.

No published output for this release. The frozen task contract remains available for audit.
Test contract

What this game measures.

buildmechanicsstateinputstability
Atomic testCategoryPointsCase
build build 5 build
merge-once mechanics 20 merge-once
valid-spawn mechanics 10 valid-spawn
terminal-state mechanics 15 terminal-state
directional-move mechanics 15 directional-move
clean-reset state 10 clean-reset
deterministic-seed state 10 deterministic-seed
keyboard-input input 10 keyboard-input
rapid-input stability 5 rapid-input

Runtime contract

The game is evaluated at 1280 × 720 with Node 22, deterministic seed reset, controlled time, native input, and schema-validated snapshots.

Frozen identity

Task content
sha256:d83a6bb137b39facd1fc98ebf6c2422ff7d0de15378efc7784984ebef9d8f121

Benchmark release
v0.1.2 release contract