Identity
- Type
- open community
- Country label
- China
- HQ country
- China
- Founding country
- China
- Parent
- not in the notes
- Parent country
- not in the notes
- Country basis
- the research notes
Where this comes from
Convention D1: a dual label, HQ first, when the HQ, founding or parent country differ.
Models by Class
Models
ModelClassOpennessParametersReleased
MiniCPM RobotManip and RobotTrackrobot policy18 Jul 2026MiniCPM5 1Bedge LLM21 May 2026MiniCPM-o 4.5multimodal LLM3 Feb 2026MiniCPM4.1 8Bedge LLM5 Sep 2025MiniCPM-V 4.5multimodal LLM24 Aug 2025MiniCPM4 / 4.1edge LLM6 Jun 2025MiniCPM4 0.5Bedge LLM6 Jun 2025MiniCPM4 8Bedge LLM6 Jun 2025MiniCPM-omultimodal LLM12 Jan 2025MiniCPM-o 2.6multimodal LLM12 Jan 2025MiniCPM-V 2.6multimodal LLM4 Aug 2024MiniCPM-Llama3-V 2.5multimodal LLM19 May 2024MiniCPM-Vmultimodal LLM1 Feb 2024BitCPM4 0.5Bedge LLM–BitCPM4 1Bedge LLM–MiniCPM-V 4.6 1.3Bmultimodal LLM–MiniCPM3-1Bedge LLM–OpenBMB VoxCPM2speech synthesis–Links
OrganisationOpenBMB (Tsinghua NLP Lab and ModelBest)open community, China
OpenBMB (Tsinghua NLP Lab and ModelBest)open community, ChinaModelsMiniCPM RobotManip and RobotTrackOpenBMB (Tsinghua NLP Lab and ModelBest), robot policyMiniCPM5 1BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMMiniCPM-o 4.5OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMMiniCPM4.1 8BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLM+14 more
MiniCPM RobotManip and RobotTrackOpenBMB (Tsinghua NLP Lab and ModelBest), robot policyMiniCPM5 1BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMMiniCPM-o 4.5OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMMiniCPM4.1 8BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLM+14 moreUse Casesnone recorded
Who Runs Itnone recorded
Models 18
MiniCPM4 / 4.1OpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperMiniCPM-VOpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperBitCPM4 1BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperBitCPM4 0.5BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperMiniCPM-Llama3-V 2.5OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM-oOpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM-V 2.6OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM-V 4.5OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM-V 4.6 1.3BOpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM3-1BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperMiniCPM4 0.5BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperMiniCPM4 8BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloper+6
MiniCPM4.1 8BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperMiniCPM-o 2.6OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM-o 4.5OpenBMB (Tsinghua NLP Lab and ModelBest), multimodal LLMDeveloperMiniCPM5 1BOpenBMB (Tsinghua NLP Lab and ModelBest), edge LLMDeveloperMiniCPM RobotManip and RobotTrackOpenBMB (Tsinghua NLP Lab and ModelBest), robot policyDeveloperOpenBMB VoxCPM2OpenBMB (Tsinghua NLP Lab and ModelBest), speech synthesisDeveloperScores
| Benchmark | Model | Score | Who ran it | Setting |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index | MiniCPM-V 4.6 1.3B | 13 index | independent | |
| MMMU-Pro | MiniCPM-V 4.6 1.3B | 38 % | independent | Reported in Artificial Analysis article; run origin not stated |
Where this comes from
Every recorded score of this organisation's models, with who ran it. Scores from different settings are not directly comparable.
Sources
- huggingface.co/openbmb/MiniCPM4.1-8B-Eagle3/blob/main/README... https://huggingface.co/openbmb/MiniCPM4.1-8B-Eagle3/blob/main/README.md
- OpenBMB launches MiniCPM-V 4.6 1.3B Instruct artificialanalysis.ai https://www.artificialanalysis.ai/articles/openbmb-launches-minicpm-v-4-6-1-3b-instruct
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "OpenBMB (Tsinghua NLP Lab and ModelBest)", https://aurion.semai.id/organisations/openbmb/, records of October 2026.