Document Arena

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

May 12, 2026
157,554 votes
24 models
Rank Spread
1
14
Anthropic
Anthropic · Proprietary
1522±8
11,934$5 / $251M
2
14
Anthropic
Anthropic · Proprietary
1513±7
20,354$5 / $251M
3
15
Anthropic
Anthropic · Proprietary
1510±8
6,695$5 / $251M
4
17
Anthropic
Anthropic · Proprietary
1509±8
6,402$5 / $251M
5
37
OpenAI · Proprietary
1496±9
4,615$5 / $301.1M
6
47
Anthropic
Anthropic · Proprietary
1495±6
31,885$3 / $151M
7
47
OpenAI · Proprietary
1492±9
4,672$5 / $301.1M
8
810
OpenAI · Proprietary
1474±7
14,439$2.50 / $151.1M
9
812
Anthropic
Anthropic · Proprietary
1466±10
8,015$5 / $25200K
10
915
Moonshot · Modified MIT
1454±10
3,769$0.95 / $4262.1K
11
817
Meta
Meta · Proprietary
1452±19
868N/AN/A
12
915
Anthropic
Anthropic · Proprietary
1450±7
16,693$3 / $15200K
13
1015
Google · Proprietary
1443±6
24,873$2 / $121M
14
1017
Google · Proprietary
1439±9
10,773$2 / $121M
15
1018
Moonshot · Modified MIT
1437±8
10,471$0.60 / $3N/A
16
1320
Google · Proprietary
1427±6
19,978$1.25 / $101M
17
1323
Google · Apache 2.0
1424±10
4,360N/AN/A
18
1522
Anthropic
Anthropic · Proprietary
1423±7
17,855$1 / $5200K
19
1624
1420±8
6,807$2 / $62M
20
1624
Google · Proprietary
1418±9
7,202$0.50 / $31M
21
1724
OpenAI · Proprietary
1411±9
7,110$1.75 / $14400K
22
1924
OpenAI · Proprietary
1407±6
22,399$1.75 / $14400K
23
1724
OpenAI · Proprietary
1407±10
3,503$5 / $301.1M
24
1824
OpenAI · Proprietary
1407±9
8,281$1.25 / $10400K

Remove Style Control Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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