Codesota · Models · Hierarchical Table RecognizerTakaya Kawakatsu3 results · 1 benchmarks
Model card

Hierarchical Table Recognizer.

Takaya Kawakatsutable-recognition

Non-causal attention with parallel inference algorithm for fast table cell content recognition. arXiv:2512.21083 (Dec 2025).

§ 01 · Benchmarks

Every benchmark Hierarchical Table Recognizer has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-all-samples96.6%#1/11source ↗
02table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-complex-samples95.1%#1/11source ↗
03table-recognition-challenge-mini-testComputer Vision · Table Recognitionteds-simple-samples98.1%#2/11source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where Hierarchical Table Recognizer actually performs.

Computer Vision
1
benchmark
avg rank #1.3
§ 05 · Sources & freshness

Where these numbers come from.

paper
3
results
0 of 3 rows marked verified.