Grok 4.3 3 months ago
I have a standard test to look at the reasoning capabilities of a model - solve today's NYTimes connections problem. Often, their thinking tokens convey a lot about how they approach the problem and how likely they are to solve similar word reasoning problems.
Claude 4.7 and Gemini 3.1 Pro have nailed all so far, GPT 5.5 failed miserably. Of the chinese models, Kimi-K-2.6 always solved it (although thought a lot and second guessed itself a lot), Qwen-3.6-Plus often gave wrong answers and GLM-5.1 just spun around endlessly until I had to stop it.
Grok-4.3 also nailed today's puzzle.