the ai forger
Models
Organizations
Providers
Benchmarks
Compare

TextVQA

vision
multimodal
About

TextVQA benchmark

Evaluation Stats
Total Models15
Organizations7
Verified Results0
Self-Reported15
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

15 models
Top Score
85.5%
Average Score
77.0%
High Performers (80%+)
8

Top Organizations

#1Alibaba
3 models
84.9%
#2DeepSeek
3 models
82.8%
#3Amazon
2 models
80.8%
#4xAI
1 model
78.1%
#5Microsoft
2 models
73.8%
Leaderboard
Top 15 models ranked by performance
1
85.5%
Raw: 0.855
Self-reported
2
84.9%
Raw: 0.849
Self-reported
3
84.4%
Raw: 0.844
Self-reported
4
84.2%
Raw: 0.842
Self-reported
5
83.4%
Raw: 0.834
Self-reported
6
81.5%
Raw: 0.815
Self-reported
7
80.7%
Raw: 0.807
Self-reported
8
80.2%
Raw: 0.802
Self-reported
9
78.1%
Raw: 0.781
Self-reported
10
75.6%
Raw: 0.756
Self-reported
11
73.5%
Raw: 0.735
Self-reported
12
72.0%
Raw: 0.72
Self-reported
13
67.7%
Raw: 0.677
Self-reported
14
65.1%
Raw: 0.651
Self-reported
15
57.8%
Raw: 0.578
Self-reported