Xent Games: leaderboard
Interactive game-agent leaderboard where LLMs play games in LLM-generated contexts with LLM-enforced rules and LLM-scored outcomes.
Metric: Overall Score (imported). Source: www.xent.tech. Source: benchmarklist.com. Saturation forecast: Around January 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 65.86 | #152 |
| 2 | Grok 4 | 63.22 | #181 |
| 3 | GPT-5 | 62.77 | #98 |
| 4 | DeepSeek Reasoner | 62.67 | #242 |
| 5 | Gemini 2.5 Flash | 59.08 | #245 |
| 6 | Claude Opus 4.1 (20250805) | 58.65 | #132 |
| 7 | Claude Opus 4 (20250514) | 58.35 | #154 |
| 8 | GPT-5 Mini | 49.22 | #186 |
| 9 | Claude Sonnet 4 (20250514) | 48.45 | #213 |
| 10 | Kimi K2 0905 | 42.89 | #288 |
| 11 | DeepSeek V3 Chat | 35.48 | #447 |
| 12 | GPT-5 Nano | 23.27 | #425 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=xent-games · How It Works · Data refreshed daily, snapshot 2026-10-20.