multimodal benchmark
ImageMining
ImageMining evaluates multimodal models on extracting structured information from images using tool use, measuring ability to combine visual understanding with tool-based retrieval and analysis.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
ImageMining Ranking
Higher score ranks better on this benchmark.
| 1 | ZA | 30.7% | 100.0% | 1 | C |
ImageMining Highlights
The leading models and scores on this benchmark.
What is ImageMining?
What ImageMining measures and how its scores work.
ImageMining evaluates multimodal models on extracting structured information from images using tool use, measuring ability to combine visual understanding with tool-based retrieval and analysis.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ImageMining
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- imagemining|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ImageMining.
Which model scores highest on ImageMining?
GLM-5V-Turbo is currently ranked first with 30.7%.
What does ImageMining measure?
ImageMining evaluates multimodal models on extracting structured information from images using tool use, measuring ability to combine visual understanding with tool-based retrieval and analysis.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.