external benchmark

TextVQA leaderboard

Every model the catalog carries a published TextVQA value for, ranked by that value.

Categoryexternal

MeasureProvider-reported validation scores; metric/scorer not disclosed

Published byTowards VQA Models That Can Read

TextVQA requires reading and reasoning about text in images. These two own-provider reports use the validation split, with metric and scorer left undisclosed in the original model cards.

No model in the catalog has a published TextVQA score.

The benchmark is defined by Towards VQA Models That Can Read, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

About TextVQA

What the benchmark measures and how its value is published, from the source’s own record.

What is TextVQA?

TextVQA is an external benchmark published by Towards VQA Models That Can Read. TextVQA requires reading and reasoning about text in images. These two own-provider reports use the validation split, with metric and scorer left undisclosed in the original model cards.

How is TextVQA scored?

Each model's result is published by Towards VQA Models That Can Read as provider-reported validation scores; metric/scorer not disclosed. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.

All leaderboards

Explore models

Top 1-5

Top 6-10

Featured

Capabilities

Benchmarks

Compare

Featured model comparisons

Featured provider comparisons

Articles