gpt-oss-120b only has 5B active parameters, so its not surprising Qwen3.8 27B outperforms it (Qwen3.8 is also ~13 months newer, which is forever in LLMs)

Fair enough. I’ve barley touched oss-120b, so i didn’t know it was so few active params. For a direct comparison, qwen3.6-35b-a3b is still better at coding than oss-120b.

And Qwen3.8-27b is still better at coding than opus 4.1.

Yes, if you list off models 27b is better than it’s all older models. But that’s my point - newer models are better than older models at the same AND much smaller size. That’s because model size matters less than they say. Training data and model architecture matter more.

No, it’s not the active parameters. Qwen 3.8 Flash has 6B active and it smokes both models.