BlogLLM Benchmark Scores as Published, Side by Side
MMAU: Results as Published
Every result the catalog holds for MMAU: 2 models from 2 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Multimodal UnderstandingMaintainer S Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, and Dinesh Manocha (University of Maryland, College Park, and Adobe)Introduced 2024Data version 2026103001, as of 2026-10-30
MMAU, Massive Multi-Task Audio Understanding and Reasoning, tests whether a model can answer questions about audio. It has 10k curated clips of speech, environmental sound, and music, paired with human-written questions and answers that require information extraction or reasoning across 27 skills. The project page shows the questions with listed answer options. The paper scores accuracy.
MMAU
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 82.5% | Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15 | Effort: high |
| InklingThinking Machines, released 2026-07-14 | 77.2% | Thinking Machines, Thinking Machines Inkling model cardchecked 2026-10-15 | Effort: 0.99 |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.