Code Model Training Transformer Models

There are 8 code model training models tracked. The highest-rated is oripress/AlgoTune at 46/100 with 95 stars.

Get all 8 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=code-model-training&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	oripress/AlgoTune AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and...	46	Emerging	95	Python
2	xjywhu/Awesome-Multimodal-LLM-for-Code Multimodal Large Language Models for Code Generation under Multimodal Scenarios	33	Emerging	221	—
3	jie-jw-wu/human-eval-comm HumanEvalComm: Evaluating Communication Skill of Code LLM and LLM Agent	31	Emerging	11	Python
4	juyongjiang/CodeUp CodeUp: A Multilingual Code Generation Llama-X Model with...	30	Emerging	127	Python
5	TingjiaInFuture/pixrep Let LLMs see your codebase just like you do.	27	Experimental	9	Python
6	Gen-Verse/ReasonFlux [NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux,...	27	Experimental	524	Python
7	xlang-ai/text2reward [ICLR 2024 Spotlight] Text2Reward: Reward Shaping with Language Models for...	22	Experimental	201	Jupyter Notebook
8	amazon-science/llm-code-preference Training and Benchmarking LLMs for Code Preference.	22	Experimental	38	Python