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

Learn more

Min
Max

Min
Max

Min
Max

Min
Max

Text Arena🏆Overall

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Jul 19, 2026
7,399,550 votes
27 labs
Rank by
Lab Rank
Model Score
Rank Spread
1
Anthropic
Anthropic
claude-opus-4-6-thinking · Proprietary
1502±4
1
13
2
Meta
Meta
muse-spark-1.1 · Proprietary
1483±7
5
314
3
Google
gemini-3.6-flash · Proprietary
1481±9
7
317
4
Alibaba
qwen3.7-max-preview · Proprietary
1476±10
11
424
5
Moonshot
kimi-k3 · Proprietary
1474±10
13
526
6
OpenAI
gpt-5.4-high · Proprietary
1470±4
16
924
7
Baidu
ernie-5.1 · Proprietary
1468±5
18
1126
8
Z.ai
glm-5.1
1465±5
20
1127
9
Xiaomi
mimo-v2.5-pro
1462±4
24
1231
10
SpaceXAI
grok-4.20-beta-0309-reasoning · Proprietary
1452±4
32
2547
11
DeepSeek
deepseek-v4-pro
1450±4
34
2653
12
Bytedance
Bytedance
dola-seed-2.0-pro · Proprietary
1448±4
37
2854
13
Amazon
amazon-nova-experimental-chat-26-02-10 · Proprietary
1448±10
38
2466
14
Thinking Machines
Thinky
inkling
1445±9
42
2767
15
Nvidia
nvidia-nemotron-3-ultra-550b-a55b-nvfp4
1443±7
48
2968
16
MiniMax
minimax-m3
1436±5
63
3973
17
Mistral
mistral-large-3
1430±3
69
6089
18
Meituan
longcat-flash-chat-2602-exp · Proprietary
1426±5
75
6499
19
Tencent
Tencent
hunyuan-vision-1.5-thinking · Proprietary
1406±12
118
81134
20
Stepfun
StepFun
step-3.5-flash
1404±4
121
108130
21
Ant Group
ling-flash-2.0
1363±7
160
144172
22
Inception AI
mercury-2 · Proprietary
1357±10
165
148177
23
intellect-3
1356±8
167
150176
24
Cohere
Cohere
command-a-03-2025
1331±3
190
178197
25
Ai2
olmo-3.1-32b-instruct
1312±6
204
195212
26
IBM
granite-4.1-8b
1293±10
217
205237
27
Microsoft
phi-4
1217±5
276
267278

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