Game playing on TicTacToe
56.6Win RateTicTacToe Specialist
Evaluation results
| Method | Links | |
|---|---|---|
| TicTacToe SpecialistOpponent=Gemini-2.0-Flash2025.06 | 56.6 | |
| Multi-Game ModelOpponent=Gemini-2.0-Flash2025.06 | 54.3 | |
| Instruct ModelOpponent=Gemini-2.0-Flash2025.06 | 52.7 | |
| Kuhn Poker SpecialistOpponent=Gemini-2.0-Flash2025.06 | 31 | |
| Simple Negotiation SpecialistOpponent=Gemini-2.0-Flash2025.06 | 27.7 | |
| Random PolicyOpponent=Gemini-2.0-Flash2025.06 | 24.5 | |
| Base ModelOpponent=Gemini-2.0-Flash2025.06 | 17.5 |