Hugging Face Evaluations

Source-qualified evaluations, report statistics and safety observations.

lightonai/LightOnOCR-3-4B

layout · 68.3 source-defined score; unit unspecified

lightonai/LightOnOCR-3-1B

table · 84.8 source-defined score; unit unspecified

JetBrains/Mellum2-12B-A2.5B-Instruct-SFT

diamond · 38.9 source-defined score; unit unspecified

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace