• New Chat
  • Leaderboard
  • Search
Terms of UsePrivacy Policy
Start Voting
Overview
Agent
Start Voting
Agent

Min
Max

Min
Max

Min
Max

Min
Max

Document Arena

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

Jul 26, 2026
322,650 votes
38 models
Rank Spread
1
14
Anthropic
claude-opus-5-high
Anthropic · Proprietary
1520±15
1,663$5 / $251M
2
16
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1510±6
37,271$5 / $251M
3
16
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1506±7
24,973$5 / $251M
4
17
Anthropic
claude-fable-5
Anthropic · Proprietary
1504±9
5,792$10 / $501M
5
29
Anthropic
claude-opus-4-7
Anthropic · Proprietary
1498±7
18,990$5 / $251M
6
29
Anthropic
claude-opus-4-7-thinking
Anthropic · Proprietary
1497±7
18,793$5 / $251M
7
514
gpt-5.5-high
OpenAI · Proprietary
1485±7
16,816$5 / $301.1M
8
716
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1483±6
54,427$3 / $151M
9
718
gpt-5.5
OpenAI · Proprietary
1480±7
17,286$5 / $301.1M
10
519
gpt-5.6-terra-xhigh
OpenAI · Proprietary
1479±13
1,969N/AN/A
11
420
gpt-5.6-sol-xhigh
OpenAI · Proprietary
1479±17
1,152N/AN/A
12
719
Anthropic
claude-opus-4-8-thinking
Anthropic · Proprietary
1475±8
8,388$5 / $251M
13
721
Meta
muse-spark-1.1
Meta · Proprietary
1472±13
2,054$1.25 / $4.251M
14
721
Anthropic
claude-sonnet-5-high
Anthropic · Proprietary
1470±10
3,601$2 / $101M
15
820
gpt-5.4
OpenAI · Proprietary
1470±7
29,809$2.50 / $151.1M
16
821
Anthropic
claude-opus-4-8
Anthropic · Proprietary
1469±8
8,193$5 / $251M
17
922
gemini-3.5-flash-medium
Google · Proprietary
1465±10
3,689$1.50 / $91M
18
925
gpt-5.6-luna-xhigh
OpenAI · Proprietary
1462±13
1,888N/AN/A
19
1024
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1462±10
7,965$5 / $25200K
20
1226
grok-4.5
SpaceXAI · Proprietary
1454±12
2,435$2 / $6500K
21
1725
kimi-k2.6
Moonshot · Modified MIT
1451±8
11,181$0.95 / $4262.1K
22
1827
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1446±7
28,634$3 / $15200K
23
1827
gemini-3.1-pro-preview
Google · Proprietary
1445±6
45,162$2 / $121M
24
1432
Meta
muse-spark
Meta · Proprietary
1443±18
1,078N/AN/A
25
1930
qwen3.7-plus
Alibaba · Proprietary
1440±11
3,088$0.32 / $1.281M
26
2132
minimax-m3
MiniMax · MiniMax Community License
1435±8
6,263$0.60 / $2.40N/A
27
2232
gemini-3-pro
Google · Proprietary
1433±9
10,739$2 / $121M
28
2433
kimi-k2.5-thinking
Moonshot · Modified MIT
1429±7
19,891$0.60 / $3N/A
29
2434
gemma-4-31b
Google · Apache 2.0
1424±8
10,577N/AN/A
30
2434
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1423±6
30,937$1 / $5200K
31
2534
gemini-2.5-pro
Google · Proprietary
1421±6
24,963$1.25 / $101M
32
2537
glm-5v-turbo
Z.ai · Proprietary
1417±10
4,894$1.20 / $4202.8K
33
2937
grok-4.20-beta-0309-reasoning
SpaceXAI · Proprietary
1414±7
18,666$2 / $62M
34
2838
gemini-3-flash
Google · Proprietary
1413±9
7,173$0.50 / $31M
35
3238
gpt-5.2-high
OpenAI · Proprietary
1405±10
7,073$1.75 / $14400K
36
3238
gpt-5.5-instant
OpenAI · Proprietary
1402±8
8,442$5 / $301.1M
37
3238
gpt-5.1
OpenAI · Proprietary
1401±9
8,220$1.25 / $10400K
38
3438
gpt-5.2
OpenAI · Proprietary
1400±6
28,068$1.75 / $14400K

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)

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

USE CASES

  • Chat with AI
  • Build Apps & Websites
  • Write & Edit Text
  • Search the Web
  • Generate Images
  • Generate Videos
  • Chose any model
  • Compare Models Side by Side

LEADERBOARD RANKINGS

  • Overall
  • Agent
  • Text
  • WebDev
  • Image-to-WebDev
  • Text to Image
  • Image Edit
  • Text to Video
  • Image to Video
  • Video Edit
  • Vision
  • Document
  • Search

COMPANY

  • About Us
  • How It Works
  • Blog
  • Careers
  • Changelog
  • Help Center
  • FAQ

LEGAL

  • Terms
  • Privacy
  • Cookies

FOLLOW

  • X
  • LinkedIn
  • YouTube
  • Discord

© Arena Intelligence 2026