Poker Gameplay on Limit Texas Hold'em (test)
43NFSPGPT-4.1-mini
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-4.1-miniModel type=Closed-source2026.01 | 43 | 0 | -24 | -205 | -46.7 | |
| LLama3-8BModel size=8B2026.01 | 8 | -177.5 | -58 | -206.5 | -108.5 | |
| Qwen2.5-72BModel size=72B2026.01 | 6 | -53.5 | -73.5 | -57.5 | -44.6 | |
| GPT-4oModel type=Closed-source2026.01 | -40.5 | -45.5 | -32 | -167 | -71.2 | |
| Qwen2.5-7BModel size=7B2026.01 | -53.5 | -188 | -144 | -101 | -121.6 | |
| Qwen3-8BModel size=8B2026.01 | -69 | -73.5 | -69 | -73.5 | -71.2 | |
| o4-miniModel type=Closed-source2026.01 | -105 | 111 | -58 | -117 | -42.2 | |
| Qwen2.5-3BModel size=3B2026.01 | -131.5 | -232.5 | -136 | -323.5 | -205.8 |