Reasoning Evaluation on Limit Texas Hold’em
2Hit RateProfessional
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Professional2026.01 | 2 | 2 | 2 | 2 | |
| o4-mini2026.01 | 1.57 | 1.65 | 1.88 | 1.7 | |
| Qwen2.5-72BModel Size=72B2026.01 | 1.03 | 1.52 | 1.85 | 1.46 | |
| Qwen2.5-7BModel Size=7B2026.01 | 1 | 0.87 | 1.7 | 1.19 | |
| GPT-4.1-mini2026.01 | 0.95 | 1.61 | 1.87 | 1.47 | |
| Qwen2.5-3BModel Size=3B2026.01 | 0.55 | 0.3 | 1.6 | 0.81 |