LLMsPark - Who Is Spy: leaderboard
Metric: Elo Rating. Source: llmsparks.github.io. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen-14B-Chat | 77 |
| 2 | GPT-3.5 Turbo | 60 |
| 3 | GPT-4 | 59 |
Interactive version: theaggregate.ai/benchmark?slug=llmspark-who-is-spy · How It Works · Data refreshed daily, snapshot 2026-09-05.