build · level 1
· Benchmark 0.3.0
2048
2048 · build.2048.v2
2.0.0task version
10atomic 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 test | Category | Points | Case |
|---|---|---|---|
| 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 | 5 | deterministic-seed |
| keyboard-input | input | 10 | keyboard-input |
| rapid-input | stability | 5 | rapid-input |
| run-seed | state | 5 | run-seed |
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 contentsha256:6185ea4e766acde99f4d4df354defc487eebaca7d5149d531799b580ebac7486
Benchmark release
v0.3.0 release contract