Comment by easygenes 2 days ago Other benchmark aggregates are less favorable to GPT-OSS-120B: https://arxiv.org/abs/2508.12461 5 comments easygenes Reply petesergeant 2 days ago With all these things, it depends on your own eval suite. gpt-oss-120b works as well as o4-mini over my evals, which means I can run it via OpenRouter on Cerebras where it's SO DAMN FAST and like 1/5th the price of o4-mini. indigodaddy 2 days ago How would you compare gpt-oss-120b to (for coding):Qwen3-Coder-480B-A35B-InstructGLM4.5 AirKimi K2DeepSeek V3 0324 / R1 0528GPT-5 MiniThanks for any feedback! petesergeant 2 days ago I’m afraid I don’t use any of those for coding 2 replies →
petesergeant 2 days ago With all these things, it depends on your own eval suite. gpt-oss-120b works as well as o4-mini over my evals, which means I can run it via OpenRouter on Cerebras where it's SO DAMN FAST and like 1/5th the price of o4-mini. indigodaddy 2 days ago How would you compare gpt-oss-120b to (for coding):Qwen3-Coder-480B-A35B-InstructGLM4.5 AirKimi K2DeepSeek V3 0324 / R1 0528GPT-5 MiniThanks for any feedback! petesergeant 2 days ago I’m afraid I don’t use any of those for coding 2 replies →
indigodaddy 2 days ago How would you compare gpt-oss-120b to (for coding):Qwen3-Coder-480B-A35B-InstructGLM4.5 AirKimi K2DeepSeek V3 0324 / R1 0528GPT-5 MiniThanks for any feedback! petesergeant 2 days ago I’m afraid I don’t use any of those for coding 2 replies →
With all these things, it depends on your own eval suite. gpt-oss-120b works as well as o4-mini over my evals, which means I can run it via OpenRouter on Cerebras where it's SO DAMN FAST and like 1/5th the price of o4-mini.
How would you compare gpt-oss-120b to (for coding):
Qwen3-Coder-480B-A35B-Instruct
GLM4.5 Air
Kimi K2
DeepSeek V3 0324 / R1 0528
GPT-5 Mini
Thanks for any feedback!
I’m afraid I don’t use any of those for coding
2 replies →