The GLM-5 repository presents language models for agentic engineering and coding.
Open source
24 alternativesWizardLM
WizardLM collects language models developed with Evol-Instruct, including WizardCoder and WizardMath.
About WizardLM
WizardLM is a GitHub repository that collects language models developed with Evol-Instruct, including the WizardLM, WizardCoder and WizardMath families. It hosts Evol-Instruct data and training code, links to Hugging Face checkpoints for each release, and reports benchmark results such as HumanEval, HumanEval+, MBPP, GSM8k, MATH, MT-Bench and AlpacaEval for model sizes ranging from 1B to 70B. Papers for WizardLM and WizardCoder are listed as published at ICLR 2024.
License terms differ by model. WizardLM-70B-V1.0 and WizardLM-13B-V1.2 are listed under the Llama 2 License, while several earlier WizardLM versions are marked non-commercial. No pricing information is given.
Key features
- Collects WizardLM, WizardCoder and WizardMath models built with Evol-Instruct
- Includes Evol-Instruct data and training code folders
- Links to Hugging Face checkpoints for released models
- Reports scores on HumanEval, MBPP, GSM8k, MATH, MT-Bench and AlpacaEval
- Covers model sizes from 1B to 70B
- Provides a demo folder and paper citations
Best for: Researchers and developers who want to study the Evol-Instruct approach and evaluate the project's released model checkpoints.
Good for
- Brings several model families and sizes together in one repository
- Benchmark tables list results for each released checkpoint
- Includes Evol-Instruct data, training code and paper references
Watch out for
- License terms vary by model, with some releases marked non-commercial and others under the Llama 2 License
- Benchmark figures are reported by the project rather than independently verified
WizardLM at a glance
- Website
- github.com/nlpxucan/WizardLM
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
WizardLM alternatives
Tools and sites you could use instead, ranked by how closely they match.
The Qwen3 model series was developed by the Qwen team at Alibaba Cloud.
Qwen3-Omni understands text, audio, images, and video, and can generate speech in real time.
Open source
24 alternatives
MobiLlama is a small language model designed for edge devices, according to its repository description.
Open source
24 alternatives
This repository accompanies research on improving language model factuality and reasoning through multi-agent debate.
This repository contains the DeepSeek-V3 language model project and related source files.
Open source
24 alternativesPopular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvla
WizardLM FAQ
What license applies to the WizardLM models?
License terms differ by release. WizardLM-70B-V1.0 and WizardLM-13B-V1.2 are listed under the Llama 2 License, while several earlier WizardLM versions are marked non-commercial.
Where can the model weights be obtained?
Each model row in the tables links to a Hugging Face checkpoint.
Which benchmarks does the repository report?
WizardCoder results cover HumanEval, HumanEval+, MBPP and MBPP+; WizardMath covers GSM8k and MATH; WizardLM covers MT-Bench, AlpacaEval, GSM8k and HumanEval.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.