Benchmark RadarAI BENCHMARK PROFILE
BanglaWild
BanglaWild is a benchmark of 2,535 Bengali scene text images with verbatim gold transcriptions and diagnostic attributes. It evaluates OCR and vision-language models on in-the-wild scene text recognition.
- Released
- 2026-08-04
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Fills the gap of measuring in-the-wild Bengali scene text recognition, providing a common testbed for OCR and VLMs and enabling analysis of error types.
Motivation
In-the-wild Bengali scene text recognition is largely unmeasured: existing resources target handwritten documents or constrained sign-board parsing, report only aggregate edit-distance metrics, and evaluate either conventional OCR or VLMs, never both on the same in-the-wild data.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.