GACL - Surround Morris — leaderboard

Game Agent Coding League: Surround Morris sub-benchmark. LLMs write code agents to play a mill/morris board game variant.

Metric: Normalized Score (0-100). Source: gameagentcodingleague.com. Status: saturation imminent. 21 models tracked.

Top models

#ModelScore
1GPT-5.579.27
2DeepSeek V4 Pro75.47
3Claude Opus 4.768.44
4GPT-5.468.07
5Kimi K2.666.46
6Qwen 3.6 Plus63.23
7Gemini 3.1 Pro (Preview)60.73
8Claude Opus 4.653.7
9Claude Sonnet 4.651.67
10GLM-5.148.85
11MiniMax-M2.748.33
12Gemma 4 31B (IT)48.18
13DeepSeek V4 Flash42.4
14Qwen 3.6 Max Preview41.61
15MiMo-V2.5-Pro37.86

Interactive version: theaggregate.ai/benchmark?slug=gacl-surround-morris · How the rankings work · Data refreshed daily, snapshot 2026-07-22.