Document Arena

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

Apr 26, 2026
118,600 votes
23 models
Rank Spread
1
14
Anthropic
Anthropic · Proprietary
1526±9
8,848$5 / $251M
2
14
Anthropic
Anthropic · Proprietary
1520±8
15,731$5 / $251M
3
16
Anthropic
Anthropic · Proprietary
1515±11
3,310$5 / $251M
4
17
Anthropic
Anthropic · Proprietary
1511±11
3,179$5 / $251M
5
37
Anthropic
Anthropic · Proprietary
1500±8
23,066$3 / $151M
6
310
OpenAI · Proprietary
1490±16
1,145$5 / $301.1M
7
411
OpenAI · Proprietary
1487±16
1,205$5 / $301.1M
8
611
OpenAI · Proprietary
1480±9
10,655$2.50 / $151.1M
9
611
Anthropic
Anthropic · Proprietary
1470±10
8,020$5 / $25200K
10
716
Moonshot · Modified MIT
1457±15
1,524$0.95 / $4262.1K
11
616
Meta
Meta · Proprietary
1457±19
842N/AN/A
12
1016
Anthropic
Anthropic · Proprietary
1450±8
13,688$3 / $15200K
13
1016
Google · Proprietary
1449±7
19,099$2 / $121M
14
1018
Moonshot · Modified MIT
1444±9
7,811$0.60 / $3N/A
15
1018
Google · Proprietary
1442±9
10,776$2 / $121M
16
1021
Google · Apache 2.0
1432±12
2,835N/AN/A
17
1421
Google · Proprietary
1429±7
16,533$1.25 / $101M
18
1422
1426±11
3,820$2 / $62M
19
1622
Anthropic
Anthropic · Proprietary
1424±8
14,707$1 / $5200K
20
1623
Google · Proprietary
1421±9
7,205$0.50 / $31M
21
1623
OpenAI · Proprietary
1414±9
7,110$1.75 / $14400K
22
1823
OpenAI · Proprietary
1410±9
8,275$1.25 / $10400K
23
2023
OpenAI · Proprietary
1406±7
18,730$1.75 / $14400K

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)

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