AV-SpeakerBench

AV-SpeakerBench is a benchmark for handling several input types together (images, documents, text). The official description says: "AV-SpeakerBench as evaluated on the LFM3-Omni-2B card: Omni table, 'Video + audio understanding' group". Below we describe in simple words what benchmarks of this type generally examine.

AV-SpeakerBench measures handling several input types together (images, documents, text). In detail, it checks:

• questions that mix text with images or document pages
• reading and extracting information from screenshots and scans
• understanding layout, titles, logos and figures in real documents
• staying accurate when the text content alone is not enough

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: AV-SpeakerBench as evaluated on the LFM3-Omni-2B card: Omni table, 'Video + audio understanding' group. Multiple-choice accuracy on video with its soundtrack (audio-visual speaker reasoning). No inventory match.

What is the AV-SpeakerBench benchmark?

AV-SpeakerBench is a benchmark for handling several input types together (images, documents, text). The official description says: 'AV-SpeakerBench as evaluated on the LFM3-Omni-2B card: Omni table, 'Video + audio understanding' group'. Below we describe in simple words what benchmarks of this type generally examine.

What does AV-SpeakerBench test?

AV-SpeakerBench mainly measures handling several input types together (images, documents, text). Concretely, it checks: questions that mix text with images or document pages; reading and extracting information from screenshots and scans; understanding layout, titles, logos and figures in real documents.

How is the AV-SpeakerBench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get AV-SpeakerBench data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/av-speakerbench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.