Document Arena

View overall rankings across AI models in document analysis and long-content reasoning.

Mar 11, 2026
43,670 votes
13 models
Rank Spread
1
11
Anthropic
Anthropic · Proprietary
1524±12
4,336$5 / $251M
2
24
Anthropic
Anthropic · Proprietary
1491±14
1,813$3 / $151M
3
24
OpenAI · Proprietary
1483±16
1,349$2.50 / $151.1M
4
25
Anthropic
Anthropic · Proprietary
1473±11
6,112$5 / $25200K
5
47
Google · Proprietary
1457±9
3,972$2 / $121M
6
58
Anthropic
Anthropic · Proprietary
1450±11
6,375$3 / $15200K
7
58
Google · Proprietary
1447±8
8,872$2 / $121M
8
811
Google · Proprietary
1430±8
6,766$1.25 / $101M
9
613
Anthropic
Anthropic · Proprietary
1427±12
5,678$1 / $5200K
10
813
Google · Proprietary
1424±9
7,303$0.50 / $31M
11
813
OpenAI · Proprietary
1413±9
5,867$1.75 / $14400K
12
913
OpenAI · Proprietary
1408±8
7,021$1.25 / $10400K
13
913
OpenAI · Proprietary
1408±8
8,280$1.75 / $14400K

Remove Style Control Leaderboard Plots

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles