Poker Agent — leaderboard
Which model can make the most money playing poker?.
Metric: TrueSkill (self-reported). Source: benchmarklist.com. Status: saturation imminent. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 1131.83 |
| 2 | GPT-5 | 1103.17 |
| 3 | Gemini 3 Flash (Preview) | 1100.21 |
| 4 | DeepSeek V3.2 | 1090.3 |
| 5 | Grok 4.1 Fast | 1079.21 |
| 6 | Claude Sonnet 4.5 | 1055.5 |
| 7 | GPT-5.1 | 1038.59 |
| 8 | Grok 4 Fast | 1034.3 |
| 9 | Claude Opus 4.5 | 1033.38 |
| 10 | Gemini 2.5 Pro | 1032.6 |
| 11 | GPT-OSS-120B | 1015.33 |
| 12 | Kimi K2 (Thinking) | 1011.63 |
| 13 | GLM-4.6 | 945.76 |
| 14 | Llama 4 Maverick | 890.5 |
Interactive version: theaggregate.ai/benchmark?slug=poker-agent · How the rankings work · Data refreshed daily, snapshot 2026-07-22.