Limit Texas Hold'em Gameplay on Limit Texas Hold'em (LHE)
2.03LHE@5 ScoreMemory w/ MEMOPILOT
Evaluation Results
| Method | Links | |
|---|---|---|
| Memory w/ MEMOPILOTPlayer Model=Qwen2.5-14B-Instruct2026.06 | 2.03 | |
| Memory w/ MEMOPILOTPlayer Model=Qwen3-235B-A22B2026.06 | 1.31 | |
| Memory w/ Gemini-3.0-FlashPlayer Model=Qwen3-235B-A22B2026.06 | 1.16 | |
| Human-Written Counter-StrategyPlayer Model=Qwen2.5-14B-Instruct2026.06 | 1.08 | |
| Human-Written Counter-StrategyPlayer Model=Qwen3-235B-A22B2026.06 | 0.39 | |
| Memory w/ Qwen2.5-7B-InstructPlayer Model=Qwen2.5-14B-Instruct2026.06 | -0.13 | |
| Memory w/ Qwen2.5-14B-InstructPlayer Model=Qwen2.5-14B-Instruct2026.06 | -0.23 | |
| Memory w/ Qwen2.5-14B-InstructPlayer Model=Qwen3-235B-A22B2026.06 | -0.29 | |
| ExpeLPlayer Model=Qwen2.5-14B-Instruct2026.06 | -0.39 | |
| ExpeLPlayer Model=Qwen3-235B-A22B2026.06 | -0.58 | |
| Memory w/ DeepSeek-V3.2Player Model=Qwen3-235B-A22B2026.06 | -0.6 | |
| Memory w/ DeepSeek-V3.2Player Model=Qwen2.5-14B-Instruct2026.06 | -0.78 | |
| ReflexionPlayer Model=Qwen3-235B-A22B2026.06 | -0.85 | |
| Memory w/ Qwen2.5-7B-InstructPlayer Model=Qwen3-235B-A22B2026.06 | -0.85 | |
| ReasoningBankPlayer Model=Qwen3-235B-A22B2026.06 | -0.87 | |
| MemoryBankPlayer Model=Qwen2.5-14B-Instruct2026.06 | -0.96 | |
| ReasoningBankPlayer Model=Qwen2.5-14B-Instruct2026.06 | -1.14 | |
| AWMPlayer Model=Qwen2.5-14B-Instruct2026.06 | -1.17 | |
| Full HistoryPlayer Model=Qwen2.5-14B-Instruct2026.06 | -1.22 | |
| Memory w/ Gemini-3.0-FlashPlayer Model=Qwen2.5-14B-Instruct2026.06 | -1.26 | |
| ReflexionPlayer Model=Qwen2.5-14B-Instruct2026.06 | -1.27 | |
| MemoryBankPlayer Model=Qwen3-235B-A22B2026.06 | -1.29 | |
| AWMPlayer Model=Qwen3-235B-A22B2026.06 | -1.32 | |
| No MemoryPlayer Model=Qwen2.5-14B-Instruct2026.06 | -1.36 | |
| Full HistoryPlayer Model=Qwen3-235B-A22B2026.06 | -1.45 | |
| No MemoryPlayer Model=Qwen3-235B-A22B2026.06 | -1.46 |