Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Game playing on Truth and Deception
Loading...
84
Win Rate
Multi-Game Model
48.224
57.512
66.8
76.088
Jun 30, 2025
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
Multi-Game Model
Opponent=Gemini-2.0-Flash
2025.06
84
Simple Negotiation Specialist
Opponent=Gemini-2.0-Flash
2025.06
82.8
Kuhn Poker Specialist
Opponent=Gemini-2.0-Flash
2025.06
81.6
TicTacToe Specialist
Opponent=Gemini-2.0-Flash
2025.06
79.9
Instruct Model
Opponent=Gemini-2.0-Flash
2025.06
75.5
Base Model
Opponent=Gemini-2.0-Flash
2025.06
49.6
Feedback
Search any
task
Search any
task