Meta launches Modality Maturity Index (MMI) multimodal benchmark with open leaderboard
_dieuwke_ · x · 2026-11-14
Meta released the Modality Maturity Index (MMI), a multimodal (audio/image/text) benchmark and official leaderboard on Hugging Face (facebook/mmi, cc-by-4.0). Top of the leaderboard: Muse-Spark-Open-816B-A42B at 15.55, Nemotron-3-Nano-Omni-30B at 13.67, Qwen3-Omni-30B at 13.54, and Thinking Machines' Inkling-Small at 12.93. Any model can be added by dropping a .evalresults/mmi.yaml into its repo or opening a PR.
More from Research
- Quantized all-to-all: NVFP4 dispatch plus RHT+S2F6 8-bit combine to fix MoE comms bottlenecks — snowclipsed · 2026-11-14
- Skeptic doubts Anthropic achieved large-factor bpb gains at fixed compute — teortaxesTex · 2026-11-14
- Quantizing training to MXFP8 with stochastic rounding: the accuracy-speed sweet spot — snowclipsed · 2026-11-14
- Ant Group's Mara Chain: refine prompts/harness/code, matches GEPA with far fewer rollouts — jiqizhixin · 2026-11-14
- Notion Ran ZeroEntropy's Reranker in Production Long Before the Acquisition — CShorten30 · 2026-11-14
- AI cracks Gödel's 1,009-page notebooks, uncovering hundreds of unknown theorems in days — stevenstrogatz · 2026-11-14