List your company

Reasoning Evaluation on Leduc Hold’em

2Hit Rate (HR)Professional
0.47120.86811.2651.6619Jan 31, 2026

Evaluation results

MethodLinks
Professional2026.012222
o4-mini2026.011.81.561.851.73
Qwen2.5-72BModel Size=72B2026.011.031.231.781.34
GPT-4.1-mini2026.010.981.731.871.52
Qwen2.5-7BModel Size=7B2026.010.950.861.681.16
Qwen2.5-3BModel Size=3B2026.010.530.181.530.74