Multi-Agent Game on MiniHanabi Co-op
85.99Average Normalized Game ScoreGPT-5-mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5-miniSource category=Closed-source2026.05 | 85.99 | |
| Strat-Reasoner-4BSource category=Open-source2026.05 | 80.19 | |
| Gemini-2.5-flashSource category=Closed-source2026.05 | 79.63 | |
| MARSHAL-4BSource category=Open-source2026.05 | 77.14 | |
| Qwen3-32BSource category=Open-source2026.05 | 72.86 | |
| Qwen3-8BSource category=Open-source2026.05 | 69.14 | |
| SPIRAL-4BSource category=Open-source2026.05 | 62.65 | |
| Gemma3-12BSource category=Open-source2026.05 | 60.25 | |
| Qwen3-4BSource category=Open-source2026.05 | 58.47 |