GLM 5.2 vs. Opus

Re:GLM 5.2 vs. Opus by jameswhitford on Monday June 22, 2026 @03:46AM (#48627043)

Hi, I am the author, I completely agree! I set out to run a vibe test on this one, not a benchmark, the real benchmarks are listed. My test shows what the models can do when both tasked with a long-running, technically difficult, one-shot task.

I think your test you describe (collaborative, task delegation, task completion, TTD, steerability) is a great format for a future test that I will definitely try out.

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by meander_water on Monday June 22, 2026 @04:01AM (#48627163)

Thanks, I didn't mean to be brusque, but I have seen a lot of these vibe tests lately that come to grand conclusions like "X model is better than Y" from the result of a single prompt.

Appreciate you sharing the results of your tests though!

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by jameswhitford on Monday June 22, 2026 @05:18AM (#48627772)

I appreciate the feedback!

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by wongarsu on Monday June 22, 2026 @04:05AM (#48627199)

Tbf, most of the "real benchmarks" have issues that are just as bad. Assessing LLM performance is just hard

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by oceansky on Monday June 22, 2026 @09:13AM (#48629694)

And personal too. Different engineers are using them for different use cases.

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by ramraj07 on Monday June 22, 2026 @01:29PM (#48633133)

The important point is that your benchmark is pretty much irrelevant for the actual usage. Thus whatever conclusion you draw is not just irrelevant but misleading.

[ Parent | on HN ]