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

Min
Max

Min
Max

Min
Max

Min
Max

Code Arena | WebDev๐Ÿ†Overall

View overall rankings across AI models on front-end web development tasks, including agentic coding workflows that require multi-step reasoning and tool use.

Aug 1, 2026
507,735 votes
43 open source models
Rank Spread
1
2
kimi-k3-max
Moonshot ยท Kimi K3 license
1676+12/-12
23
4,365$3 / $151M
2
6
glm-5.2-max
Z.ai ยท MIT
1587+9/-9
66
6,319$1.40 / $4.401M
3
22
Tencent
hy3
Tencent ยท Apache 2.0
1516+17/-17
1227
1,492$0.13 / $0.53262.1K
4
23
glm-5.1
Z.ai ยท MIT
1516+8/-8
1625
7,315$1.40 / $4.40202.8K
5
24
kimi-k2.6
Moonshot ยท Modified MIT
1510+8/-8
1827
9,257$0.95 / $4262.1K
6
28
minimax-m3
MiniMax ยท MiniMax Community License
1491+8/-8
2632
8,104$0.60 / $2.40N/A
7
32
mimo-v2.5-pro
Xiaomi ยท MIT
1473+7/-7
2837
11,299$0.43 / $0.871.1M
8
33
kimi-k2.7-code
Moonshot ยท Modified MIT
1473+10/-10
2839
4,538$0.73 / $3.50262.1K
9
35
deepseek-v4-pro-high-preview
DeepSeek ยท MIT
1465+7/-7
3140
10,618$0.43 / $0.871M
10
41
deepseek-v4-pro
DeepSeek ยท MIT
1446+7/-7
3651
11,196$0.43 / $0.871M
11
45
mimo-v2.5
Xiaomi ยท MIT
1436+7/-7
3852
10,232$0.14 / $0.281.1M
12
46
kimi-k2.5-thinking
Moonshot ยท Modified MIT
1436+6/-6
3952
15,884$0.60 / $3N/A
13
47
glm-5
Z.ai ยท MIT
1435+8/-8
3852
6,968$1 / $3.20202.8K
14
48
glm-4.7
Z.ai ยท MIT
1433+12/-12
3854
3,797$0.40 / $1.75204.8K
15
50
deepseek-v4-flash-high-preview
DeepSeek ยท MIT
1432+7/-7
4052
9,165$0.14 / $0.281M
16
53
Thinking Machines
inkling
Thinky ยท Apache 2.0
1412+10/-10
4960
4,662$1 / $4.051M
17
55
kimi-k2.5-instant
Moonshot ยท Modified MIT
1405+12/-12
5065
3,087$0.57 / $2.85262.1K
18
56
qwen3.5-397b-a17b
Alibaba ยท Apache 2.0
1400+6/-6
5165
15,750$0.39 / $2.34262.1K
19
59
minimax-m2.7
MiniMax ยท Modified MIT
1399+7/-7
5166
11,872$0.25 / $1204.8K
20
64
minimax-m2.1-preview
MiniMax ยท MIT
1388+10/-10
5370
7,291$0.30 / $1.20204.8K
21
65
minimax-m2.5
MiniMax ยท Modified MIT
1386+8/-8
5570
7,167$0.15 / $0.90204.8K
22
70
gemma-4-26b-a4b
Google ยท Apache 2.0
1367+17/-17
6179
1,415N/AN/A
23
71
gemma-4-31b
Google ยท Apache 2.0
1364+8/-8
6777
7,356$0.14 / $0.40262.1K
24
72
deepseek-v3.2-thinking
DeepSeek ยท MIT
1361+9/-9
6877
6,613$0.27 / $0.40163.8K
25
73
qwen3.5-122b-a10b
Alibaba ยท Apache 2.0
1360+8/-8
6877
7,688$0.26 / $2.08262.1K
26
74
qwen3.5-27b
Alibaba ยท Apache 2.0
1358+8/-8
6979
7,296$0.20 / $1.56262.1K
27
75
Tencent
hunyuan-hy3-preview
Tencent ยท tencent-hunyuan-community
1357+18/-18
6782
1,361N/AN/A
28
77
laguna-m.1
Poolside ยท Apache 2.0
1349+10/-10
6982
4,877$0.20 / $0.40262.1K
29
79
glm-4.6
Z.ai ยท MIT
1339+11/-11
7385
6,568$0.50 / $2204.8K
30
82
mimo-v2-flash (non-thinking)
Xiaomi ยท MIT
1331+10/-10
7685
5,413$0.10 / $0.30262.1K
31
84
deepseek-v3.2
DeepSeek ยท MIT
1323+8/-8
7985
8,905$0.27 / $0.40163.8K
32
85
kimi-k2-thinking-turbo
Moonshot ยท Modified MIT
1322+7/-7
7986
12,548$1.15 / $8262.1K
33
86
laguna-xs.2
Poolside ยท Apache 2.0
1304+11/-11
8588
3,772$0.10 / $0.20262.1K
34
87
minimax-m2
MiniMax ยท Apache 2.0
1297+11/-11
8688
6,508$0.26 / $1.02204.8K
35
88
mimo-v2-flash (thinking)
Xiaomi ยท MIT
1291+17/-17
8692
1,649$0.10 / $0.30262.1K
36
89
qwen3-coder-480b-a35b-instruct
Alibaba ยท Apache 2.0
1272+8/-8
8894
12,222$0.40 / $1.60262.1K
37
90
deepseek-v3.2-exp
DeepSeek ยท MIT
1272+14/-14
8897
3,845$0.27 / $0.41163.8K
38
91
mistral-medium-3.5
Mistral ยท Modified MIT
1267+16/-16
8899
2,076$1.50 / $7.50262.1K
39
94
qwen3.5-35b-a3b
Alibaba ยท Apache 2.0
1250+18/-18
89101
1,521$0.14 / $1262.1K
40
97
trinity-large-thinking
Apache 2.0
1239+21/-21
90101
1,274$0.22 / $0.85262.1K
41
99
mistral-large-3
Mistral ยท Apache 2.0
1230+26/-26
91103
808$0.50 / $1.50N/A
42
102
granite-4.1-8b
IBM ยท Apache 2.0
1194+19/-19
99106
1,674$0.05 / $0.10131.1K
43
103
devstral-2
Mistral ยท Modified MIT
1194+21/-21
99106
1,139N/AN/A

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

ยฉ Arena Intelligence 2026