LLMsPark - Trust Game (Single Play): leaderboard
Metric: Elo rating (initial 1000, K=32). Source: llmsparks.github.io. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | ChatGLM2 6B | 1285.09 |
| 2 | Baichuan-7B | 1106.68 |
| 3 | GPT-3.5 Turbo | 912.35 |
| 4 | Baichuan2-7B-Chat | 888.08 |
| 5 | GPT-4 | 871.8 |
| 6 | Dolly V2 12B | 858.29 |
Interactive version: theaggregate.ai/benchmark?slug=llmspark-trust-game-single-play · How It Works · Data refreshed daily, snapshot 2026-10-09.