Multi-Agent Game on Tic-Tac-Toe vs. MCTS Bot (100 sims)
90.77First-move Normalized ScoreStrat-Reasoner-4B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Strat-Reasoner-4BSource category=Open-source2026.05 | 90.77 | 81.84 | |
| GPT-5-miniSource category=Closed-source2026.05 | 88.84 | 89.73 | |
| Gemini-2.5-flashSource category=Closed-source2026.05 | 86.63 | 85.52 | |
| Qwen3-32BSource category=Open-source2026.05 | 76.53 | 76.42 | |
| MARSHAL-4BSource category=Open-source2026.05 | 73.47 | 81.55 | |
| Gemma3-12BSource category=Open-source2026.05 | 71.61 | 73.58 | |
| SPIRAL-4BSource category=Open-source2026.05 | 70.45 | 69.77 | |
| Qwen3-8BSource category=Open-source2026.05 | 69.72 | 69.39 | |
| Qwen3-4BSource category=Open-source2026.05 | 65.24 | 69.56 |