LLM Grid Game - gomoku / image / prompt 2024-06-12 / player 2: leaderboard

Metric: Win rate versus random (%). Source: research-outcome.github.io. Saturation forecast: Estimated already saturated. 6 models tracked.

Top models

#ModelScore
1Claude 3 Sonnet (20240229)100
2Gemini 1.5 Pro80
3GPT-4o60
4Gemini 1.5 Flash60
5Claude 3.5 Sonnet (20240620)20
6GPT-4 Turbo20

Interactive version: theaggregate.ai/benchmark?slug=llm-grid-game-gomoku-image-prompt-2024-06-12-player-2 · How It Works · Data refreshed daily, snapshot 2026-10-09.