the ai forger
Models
Organizations
Providers
Benchmarks
Compare

DocVQA

vision
multimodal
About

DocVQA benchmark

Evaluation Stats
Total Models26
Organizations10
Verified Results0
Self-Reported26
Benchmark Details
Max Score1
Language
en
Performance Overview
Score distribution and top performers

Score Distribution

26 models
Top Score
96.4%
Average Score
91.4%
High Performers (80%+)
25

Top Organizations

#1Alibaba
4 models
95.5%
#2Anthropic
1 model
95.2%
#3Microsoft
1 model
93.2%
#4Mistral AI
3 models
93.0%
#5Amazon
2 models
93.0%
Leaderboard
Top 20 models ranked by performance
1
96.4%
Raw: 0.964
Self-reported
2
95.7%
Raw: 0.957
Self-reported
3
95.2%
Raw: 0.952
Self-reported
4
95.2%
Raw: 0.952
Self-reported
5
94.9%
Raw: 0.9486
Self-reported
6
94.8%
Raw: 0.948
Self-reported
7
94.4%
Raw: 0.944
Self-reported
8
94.4%
Raw: 0.944
Self-reported
9
93.6%
Raw: 0.936
Self-reported
10
93.5%
Raw: 0.935
Self-reported
11
93.3%
Raw: 0.933
Self-reported
12
93.3%
Raw: 0.933
Self-reported
13
93.2%
Raw: 0.932
Self-reported
14
93.2%
Raw: 0.932
Self-reported
15
92.8%
Raw: 0.928
Self-reported
16
92.4%
Raw: 0.924
Self-reported
17
92.3%
Raw: 0.923
Self-reported
18
90.7%
Raw: 0.907
Self-reported
19
90.1%
Raw: 0.901
Self-reported
20
88.9%
Raw: 0.889
Self-reported
Showing top 20 of 26 models