battleship-vs-jev
ickas/battleship-vs-jev
A 60-game benchmark of TypeSafe's Jev evaluation model playing Battleship. The model matches plain code; it does not beat it.
Research & evaluationTypeScript
- Stars
- 0
- Forks
- 0
Review source
View cited sourceTopics
jevaibattleshipbenchmarkevaluation-metricsllm-evaluationtypescript