LLM Grid Game - connect-four / image / prompt 2024-06-12 / player 1: leaderboard
Metric: Win rate versus random (%). Source: research-outcome.github.io. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 100 |
| 2 | GPT-4o | 80 |
| 3 | GPT-4 Turbo | 80 |
| 4 | Gemini 1.5 Flash | 80 |
| 5 | Claude 3 Sonnet (20240229) | 80 |
| 6 | Gemini 1.5 Pro | 40 |
Interactive version: theaggregate.ai/benchmark?slug=llm-grid-game-connect-four-image-prompt-2024-06-12-player-1 · How It Works · Data refreshed daily, snapshot 2026-10-09.