because they're stealing from the frontier models. they're gaming the benchmarks. look how bad glm 5.2 is on cursors evals. gmhit garbage , but it gets glazed as God tier.
I never have have the issues most people talk about ... I feel like most were never Devs before ai and don't know what they actually need done when prompting. that on top of not utilizing good tools such as a codebase indexer, lsp and a project scaffold.
give it a structured plan and it it does really well compared to similar priced models. I'd never use it for anything that required heavy reasoning and it's not built for that.
they're not near opus at all, anyone using the models in a real working environment will tell you the same thing. on paper they have impressive benchmarks, but that's not realistic to actual use.
I don't think the writer has used top tier models very much. I have subscriptions to basically every provider, the difference between glm5.2 and opus is not even close, the gap is huge. raw benchmarks glm is impressive , but in practice these models are lacking so much. I had fable create a detailed implementation guide that explained how to implement everything in immense detail, it included all the libraries to use and versions. I then had deepseek v4 pro execute and it used old versions , different libraries and cut corners. Fable said about 80% was implemented wrong.
I had GLM 5.2 do the same, and it performed exceptionally better, but when it got stuck on something it would be trial and error mode going forward and have zero foresight for future issues that might occur due to fixes it was trying. the model severally lacks prompt understanding, and testing .
The absolute bane of my existence, I had a time a week ago repairing my bootloader after I (stupidly) did 3 months of windows updates after running a bunch of disk repairs and other recovery based things after I (again, stupidly) fell for a fake repo for deepseek tui and infected myself