inference/research
verifiedmedium · 0.80updated 2026-10-19

openbmb/MiniCPM-V-4.7-35B-A3B · Hugging Face

repo

Fields

id
sources/minicpm-v-4-7-35b-a3b-hf
Kind
repo
Accessed
2026-10-19
notes
Read https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B for the benchmark figures on models/minicpm-v-4-7-35b-a3b. As recorded by the reader: Values read from the official 'Overall Performance (35B-A3B, Instruct)' Language chart (row labels verified against the table's Task/Benchmark columns). Row labels as published: 'MMLU-Pro' and 'LiveCodeBench-v6'. Same chart also lists CMMLU 90.21, SuperGPQA 61.23, IFBench 47.67, AIME26@avg16 76.46, BFCL-V4 60.06, tau2-Bench 84.65, which are outside the allowed list and excluded. No GPQA Diamond figure is published for this model.

Notes

Read https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B for the benchmark figures on models/minicpm-v-4-7-35b-a3b. As recorded by the reader: Values read from the official 'Overall Performance (35B-A3B, Instruct)' Language chart (row labels verified against the table's Task/Benchmark columns). Row labels as published: 'MMLU-Pro' and 'LiveCodeBench-v6'. Same chart also lists CMMLU 90.21, SuperGPQA 61.23, IFBench 47.67, AIME26@avg16 76.46, BFCL-V4 60.06, tau2-Bench 84.65, which are outside the allowed list and excluded. No GPQA Diamond figure is published for this model.

Cross-references

This record references no other records.