List your company

Multi-Agent Game on Tic-Tac-Toe vs. MCTS Bot, 1000 sims

88.32First-move Normalized ScoreGemini-2.5-flash
64.909670.987377.06583.1427May 6, 2026

Evaluation results

MethodLinks
Gemini-2.5-flashSource category=Closed-source2026.0588.3282.53
GPT-5-miniSource category=Closed-source2026.0582.1287.1
Strat-Reasoner-4BSource category=Open-source2026.0577.673.12
MARSHAL-4BSource category=Open-source2026.0576.181.22
SPIRAL-4BSource category=Open-source2026.0574.267.84
Qwen3-32BSource category=Open-source2026.0570.3476.88
Qwen3-8BSource category=Open-source2026.0568.6272.03
Qwen3-4BSource category=Open-source2026.0566.7868.97
Gemma3-12BSource category=Open-source2026.0565.8180.02