GACL - WordMatrix — leaderboard
Game Agent Coding League: WordMatrix sub-benchmark. LLMs write code agents to play a word placement strategy game.
Metric: Normalized Score (0-100). Source: gameagentcodingleague.com. Status: saturation imminent. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.1 | 68.33 |
| 2 | Kimi K2.6 | 66.72 |
| 3 | GPT-5.5 | 66.56 |
| 4 | Gemini 3 Flash (Preview) | 65.62 |
| 5 | MiMo-V2.5-Pro | 65.62 |
| 6 | Gemini 3.1 Pro (Preview) | 65.57 |
| 7 | Claude Opus 4.7 | 65.42 |
| 8 | DeepSeek V4 Flash | 65.1 |
| 9 | GPT-5.4 | 64.84 |
| 10 | Claude Sonnet 4.6 | 64.53 |
| 11 | Grok 4.20 | 64.32 |
| 12 | Claude Opus 4.6 | 63.96 |
| 13 | DeepSeek V4 Pro | 57.81 |
| 14 | Qwen 3.6 Plus | 57.66 |
| 15 | Qwen 3.6 Max Preview | 57.29 |
Interactive version: theaggregate.ai/benchmark?slug=gacl-wordmatrix · How the rankings work · Data refreshed daily, snapshot 2026-07-22.