In the AI programming challenge "Gemstone Word Puzzle," Moonshot AI's open-source model Kimi K2.6 swept closed-source flagships like GPT-5.5, Claude Opus 4.7, and Gemini Pro 3.1 to win, with 7 wins and 1 loss, 22 points.
The challenge required models to construct valid words on sliding puzzles from 10×10 to 30×30 in 10 seconds, with long words scoring positively, short words scoring negatively. Kimi K2.6 used a greedy strategy to continuously slide, accumulating the highest score on large grids. Claude Opus 4.7 failed to complete necessary slides on large grids, while Muse Spark misunderstood the scoring rules leading to a score as low as -15309.
Full ranking: Kimi K2.6 (22 points), Xiaomi MiMo V2-Pro (20 points), GPT-5.5 (16 points), GLM 5.1 (15 points), Claude Opus 4.7 (12 points), Gemini Pro 3.1 (9 points), Grok Expert 4.2 (9 points), DeepSeek V4 (3 points), Muse Spark (0 points).
This challenge reveals an overlooked dimension in model evaluation: long-horizon reasoning strategy execution and rule understanding ability, rather than benchmark scores. Open-source models are redefining the AI programming assistant competitive landscape.