sk-bench
Harbor: pendingA native-first benchmark for evaluating generative LLMs in Slovak, comprising 30 datasets across ten skill categories with 33 scored task variants.
- Samples
- 30
- Released
- 2026
- Scores
- 13
SK-VG
SK-VG is a dataset for Scene Knowledge-guided Visual Grounding, where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge.
How to run
ltb · sk-vg
$ npm i -g lettokenburn-cli$ ltb bench info sk-vg
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
0 sourced entriesNo sourced scores recorded yet.
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
SK-VG is a dataset for Scene Knowledge-guided Visual Grounding, where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge. To perform this task, SK-VG is the first dataset of the fourth type, where for each image, we provide human-written knowledge to describe its content.