Codesota · Papers2026-01-20
Paper

LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

arXiv ↗Paper ↗
§ 01 · Benchmark results

2 results reproduced from this paper.

View:
Sorted instantly in-page
Results
2
SOTA rows
0
Models
2
Datasets
0
#ModelVendorBenchmarkValueSOTADateSource
01LightOnOCR-2-1BLightOnolmOCR-Bench83.2%source ↗
02LightOnOCR-1B-1025olmOCR-Bench76.1%source ↗
Benchmark trail
§ 02 · Models

2 models from this paper.

evaluates
LightOnOCR-2-1B
LightOn
evaluates
LightOnOCR-1B-1025
Read next

Three places to go from here.

Index
All papers
All tracked papers in the registry, with benchmark result, model, and leaderboard linkage where available.
Replacement
Papers with Code is dead — alternatives
What replaced PWC for each use case: LLMs, OCR, speech, vision, robotics.
Top hub
LLM benchmarks
Every frontier LLM benchmark, scored.