Pac-Man bench tests how well a model and harness can recreate Pac-Man from a single prompt:
SEARCH /
MODELS All ▾
None checked shows allClear
Sort
Score Cost Time Tokens
↑ Low ↓ High
\-- SHOWN
GAME OVER
No entries match.
CONTINUE?
SEARCH /
MODELS All ▾
None checked shows allClear
Sort
Score Cost Time Tokens
↑ Low ↓ High
\-- SHOWN
GAME OVER
No entries match.
CONTINUE?