GACL - WordMatrix: leaderboard
Game Agent Coding League: WordMatrix sub-benchmark. LLMs write code agents to play a word placement strategy game.
Metric: Normalized tournament points (0-100); source-selected best generated agent. Source: gameagentcodingleague.com. Saturation forecast: Around January 2027. 21 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.1 | 68.33 | #97 |
| 2 | Kimi K2.6 | 66.72 | #104 |
| 3 | GPT-5.5 | 66.56 | #31 |
| 4 | Gemini 3 Flash (Preview) | 65.63 | #82 |
| 5 | MiMo-V2.5-Pro | 65.63 | #158 |
| 6 | Gemini 3.1 Pro (Preview) | 65.57 | #58 |
| 7 | Claude Opus 4.7 | 65.42 | #49 |
| 8 | DeepSeek V4 Flash | 65.1 | #137 |
| 9 | GPT-5.4 | 64.84 | #79 |
| 10 | Claude Sonnet 4.6 | 64.53 | #90 |
| 11 | Grok 4.20 | 64.32 | #175 |
| 12 | Claude Opus 4.6 | 63.96 | #63 |
| 13 | DeepSeek V4 Pro | 57.81 | #102 |
| 14 | Qwen 3.6 Plus | 57.66 | #120 |
| 15 | Qwen 3.6 Max Preview | 57.29 | #85 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=gacl-wordmatrix · How It Works · Data refreshed daily, snapshot 2026-10-20.