Multi-Agent Game on KuhnPoker vs. NE Bot
94.04Normalized Score (First Move)Strat-Reasoner-4B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Strat-Reasoner-4BSource category=Open-source2026.05 | 94.04 | 90.47 | |
| Gemini-2.5-flashSource category=Closed-source2026.05 | 92.44 | 87.79 | |
| GPT-5-miniSource category=Closed-source2026.05 | 77.72 | 86.56 | |
| MARSHAL-4BSource category=Open-source2026.05 | 75.05 | 73.94 | |
| Qwen3-32BSource category=Open-source2026.05 | 74.95 | 76.06 | |
| Qwen3-4BSource category=Open-source2026.05 | 70.71 | 70.15 | |
| Qwen3-8BSource category=Open-source2026.05 | 68.26 | 70.05 | |
| Gemma3-12BSource category=Open-source2026.05 | 66.71 | 65.01 | |
| SPIRAL-4BSource category=Open-source2026.05 | 58.01 | 69.38 |