[storus]

In my tests, GPT-OSS-120B Q8 was close to DeepSeek R1 671B Q16 in solving graduate-level math but much faster with way fewer thinking tokens.

[overfeed]

Supporting TFA'd thesis that it's trained to be good at benchmarks.

[Mars008]

Is it bad? It was trained on synthetic data with emphasis on coding and scientific thinking. Good on my opinion, that's what it can be used for. Not as universal do it all model.