[flagged]
GLM-5.3 Artificial Analysis Benchmarks
61–64 of 64 posts
Re: GLM-5.3 Artificial Analysis Benchmarks
#62I ran the same Mac SVG drawing prompt through GLM 5.2 and 5.3 across every reasoning effort level, and 5.3 showed improved performance
Re: GLM-5.3 Artificial Analysis Benchmarks
#63Earlier quoted context omitted.
no, at subscription prices claude is a better value than GLM. They're only a better value if you're paying API rates
You can have a subscription for GLM.
yes, but the GLM subscription gives you barely more usage than you'd get just paying API rates. it's not subsidized like the claude or chatgpt subscriptions are.
Re: GLM-5.3 Artificial Analysis Benchmarks
#64Earlier quoted context omitted.
You can have a subscription for GLM.
yes, but the GLM subscription gives you barely more usage than you'd get just paying API rates. it's not subsidized like the claude or chatgpt subscriptions are.
It changed recently but previously subscription had prompt allowance, not token allowance. So probably accidentally was very genrous.