Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
legolasyiu 
posted an update 4 days ago
Post
197
We release open-weight early experimental Codeforce metatune-gpt20b, fine tuned version of OpenAI's gpt-oss-20b model, this is one of the first public release recursive self improving AI.

EpistemeAI/Codeforce-metatune-gpt20b
legolasyiu
•
edited 4 days ago

🧠 Model Benchmark Comparison

This table presents HumanEval benchmark scores across several large language models.

Model HumanEval
Codeforce-GPT-oss-20b 90
Qwen 3 235B 80
DeepSeek-R1 70B 88
Phi-4 Reasoning 88
Llama 4 Scout 78
Llama 3.3 70B 83
Gemma 3 27B 76
GPT-OSS 20B 73
GPT-OSS 120B 71
legolasyiu

Codeforce-GPT-oss-20b leads the benchmark, surpassing even larger models like Qwen 3 235B and DeepSeek-R1 70B. Its superior reasoning and code synthesis capabilities indicate an optimized training strategy rather than sheer scale dominance.
JLouisBiz

There is no description telling specifically what is that what is new with your release.

·
legolasyiu

It uses recursive self improvement techniques. It also improves coding vs others in Humaneval.

In this post