Benchmark profile
ImageMining
A multimodal retrieval and extraction benchmark over image-heavy task settings.
Data verifiedHow BenchLM shows ImageMining right now
BenchLM is tracking ImageMining in the local dataset, but exact-source verification records for these rows are still being attached. To avoid a blank benchmark page, BenchLM shows the current tracked rows below as a display-only reference table.
These tracked rows are useful for inspection and spot-checking, but until exact-source attachments are completed they should not be treated as fully verified public benchmark rows.
Tracked score on ImageMining — July 29, 2026
BenchLM mirrors the published tracked score view for ImageMining. GLM-5V-Turbo leads the public snapshot at 30.7% , followed by Kimi K2.5 (24.4%). BenchLM does not use these results to rank models overall.
Tracked score table (2 models)
ScoreAbout ImageMining
Year
2026
Tasks
Visual retrieval tasks
Format
Image-grounded retrieval and extraction
Difficulty
Multimodal retrieval
BenchLM tracks ImageMining as a display-only reference for visual retrieval and extraction performance.
BenchLM freshness & provenance
Version
ImageMining 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does ImageMining measure?
A multimodal retrieval and extraction benchmark over image-heavy task settings.
Which model leads the published ImageMining snapshot?
GLM-5V-Turbo currently leads the published ImageMining snapshot with 30.7% tracked score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on ImageMining?
2 AI models are included in BenchLM's mirrored ImageMining snapshot, based on the public leaderboard captured on July 29, 2026.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.