MMBench-Live D
AI benchmark
- Tier
- D why
- Snapshot
What is MMBench-Live?
MMBench-Live is a continuously evolving multimodal benchmark that evaluates vision-language models with automatically generated, regularly updated visual QA instances derived from MMBench.
Media mostly
“We present MMBench-Live, a continuously evolving multimodal benchmark built by a multi-agent-driven automated pipeline.”
arxiv.org/abs/2607.01813v1 ↗General capability
“Evaluation benchmarks are essential for measuring the capabilities of vision–language models (VLMs).”
github.com/PRIS-CV/MMBench-Live ↗
Paper: arxiv.org/abs/2607.01813v1 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
MMBench original
Tier D
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 2 models scored
- fewer than 5 models scored
- in curated RL directories (1 pt)
How we got to tier D
- Adoption: 2 models scored; fewer than 5 models scored. Tier D.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where MMBench-Live sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-19 snapshot.