SEEDBench (image)

SEEDBench (image) is a benchmark for understanding images combined with text. The official description says: "SEEDBench (image) as evaluated on the LFM3-Omni-2B card: image subset of SEED-Bench". Below we describe in simple words what benchmarks of this type generally examine.

SEEDBench (image) measures understanding images combined with text. In detail, it checks:

• answering questions about images (figures, photos, charts, memes)
• reading text inside images and connecting it to the question
• visual reasoning such as counting, locating and comparing objects
• combining what is seen with general knowledge

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: SEEDBench (image) as evaluated on the LFM3-Omni-2B card: image subset of SEED-Bench.

What is the SEEDBench (image) benchmark?

SEEDBench (image) is a benchmark for understanding images combined with text. The official description says: 'SEEDBench (image) as evaluated on the LFM3-Omni-2B card: image subset of SEED-Bench'. Below we describe in simple words what benchmarks of this type generally examine.

What does SEEDBench (image) test?

SEEDBench (image) mainly measures understanding images combined with text. Concretely, it checks: answering questions about images (figures, photos, charts, memes); reading text inside images and connecting it to the question; visual reasoning such as counting, locating and comparing objects.

How is the SEEDBench (image) 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 SEEDBench (image) 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/seedbench-image/scores) or pull it directly from the Open LLM Radar API with any HTTP client.