Skip to content
← Vibe Bench overview

Data visualization rankings

Best AI for data visualization

Compare models on charts and data presentation using current head-to-head Design Arena results, win rate, speed, and tournament volume.

Current source snapshot
Jul 17, 2026
127 ranked entries

Live category evidence

Current Design Arena leaderboard

How this source works →
Rank Model ELO Win rate Average time Blended price Tournament runs
2
Anthropic
Claude Fable 5
Anthropic
1,362 67.6% 117.0s $22 8,663
3 1,324 59.7% 174.6s $2 10,843
4
Anthropic
Claude Opus 4.6
Anthropic
1,321 62.0% 156.5s $11 19,598
5
Anthropic
Claude Opus 4.7
Anthropic
1,319 61.5% 102.8s $11 19,389
6
Zhipu
GLM 5.1
Zhipu
1,318 61.2% 237.3s $2.14 6,779
7
Anthropic
Claude Sonnet 4.6
Anthropic
1,316 61.0% 138.9s $6 20,153
8
Anthropic
Claude Opus 4.6 (Thinking)
Anthropic
1,313 60.6% 156.6s $11 11,862
9
xAI
Grok 4.5
xAI
1,312 58.1% 86.2s $3 5,992
10
Zhipu
GLM 5.2
Zhipu
1,311 58.6% 325.2s $2.15 11,176
11
Zhipu
GLM 5 Turbo
Zhipu
1,302 58.1% 271.0s $1.9 12,847
12
Alibaba
Qwen3.7 Max
Alibaba
1,297 57.7% 218.4s $2.21 12,830
13
OpenAI
GPT-5.5
OpenAI
1,296 58.1% 132.5s $11.25 22,204
14
Moonshot
Kimi K2.6
Moonshot
1,296 56.7% 375.0s $1.71 28,120
15
Alibaba
Qwen3.7 Plus
Alibaba
1,288 53.5% 225.3s $0.56 848
16
Xiaomi
MiMo-V2.5-Pro
Xiaomi
1,285 57.4% 248.5s $1.5 5,024
17 1,283 71.8% 71.2s $3.44 3,845
18
Anthropic
Claude Sonnet 5
Anthropic
1,281 54.4% 110.5s $4 5,230
19
Anthropic
Claude Opus 4.5
Anthropic
1,279 58.6% 92.6s $10 18,995
20
Xiaomi
MiMo-V2.5
Xiaomi
1,278 54.3% 142.9s $0.14 14,447
21
MiniMax
MiniMax M3
MiniMax
1,276 55.1% 132.8s $0.53 7,186
22
OpenAI
GPT-5 (High)
OpenAI
1,275 63.3% 148.2s $3.44 6,807
23
Anthropic
Claude Opus 4.8
Anthropic
1,271 54.8% 63.4s $10 15,466
24
MiniMax
MiniMax M2.7
MiniMax
1,269 53.7% 155.7s $0.53 14,613
25 1,269 56.3% 156.9s $5.63 10,752
26
Moonshot
Kimi K2.7 Code
Moonshot
1,268 53.0% 221.8s $1.71 10,711
27
Zhipu
GLM 5
Zhipu
1,265 53.0% 150.2s $1.55 31,968
28 1,263 52.7% 187.7s $1.3 27,045
29
Google
Gemini 3 Pro Preview
Google
1,263 60.6% 79.5s $4.5 12,275
30 1,258 54.2% 63.6s $3.38 28,872
31
Alibaba
Qwen3.6 Plus
Alibaba
1,256 50.8% 224.3s $0.73 16,468
32 1,252 54.8% 82.3s $4.5 36,203
33
Nex Agi
Nex N2 Pro
Nex Agi
1,250 48.8% 422.4s $0.44 3,681
34
xAI
Grok 4.20 Beta (Reasoning)
xAI
1,244 52.5% 96.8s $1.56 16,956
35
MiniMax
MiniMax M2.1
MiniMax
1,244 57.0% 110.8s $0.53 9,381
36
OpenAI
GPT-5.1 (Low)
OpenAI
1,242 58.0% 103.6s $3.44 10,832
37
OpenAI
GPT-5.2 (High)
OpenAI
1,239 56.1% 162.0s $4.81 1,661
38
Zhipu
GLM 5V Turbo
Zhipu
1,238 49.3% 136.8s $1.9 29,673
39
Anthropic
Claude 3.7 Sonnet
Anthropic
1,234 61.9% 88.0s 7,529
40
xAI
Grok 4.20 Beta
xAI
1,234 50.8% 67.9s $1.56 17,286
41
OpenAI
GPT-5.4 (Low)
OpenAI
1,233 52.4% 70.0s $5.63 11,777
42 1,232 55.6% 124.6s $3.44 10,709
43
OpenAI
GPT-5.1 (None)
OpenAI
1,232 55.8% 97.2s $3.44 10,899
44
Zhipu
GLM 4.7
Zhipu
1,231 51.2% 153.7s $1 29,267
45 1,231 54.6% 164.1s $3.44 8,405
46
Zhipu
GLM 4.5 Air
Zhipu
1,230 59.4% 100.0s $0.43 8,103
47
xAI
Grok 4.3
xAI
1,223 47.6% 72.8s $1.56 29,275
48
OpenAI
GPT-5.2 (Low)
OpenAI
1,222 52.0% 144.1s $4.81 13,533
49
OpenAI
GPT-5.2 (None)
OpenAI
1,219 50.3% 146.6s $4.81 16,146
50
OpenAI
GPT-5.4 (None)
OpenAI
1,218 50.2% 57.7s $5.63 13,537
51
DeepSeek
DeepSeek-R1-0528
DeepSeek
1,216 60.7% 76.0s $1.15 8,357
52
DeepSeek
DeepSeek-V4-Pro
DeepSeek
1,215 48.0% 237.1s $2.18 10,218
53
OpenAI
GPT-5 (Minimal)
OpenAI
1,214 50.7% 116.9s $3.44 17,332
54 1,212 53.2% 123.9s $1.09 4,149
55
MiniMax
MiniMax M2.5
MiniMax
1,209 51.2% 107.6s $0.44 5,389
56
OpenAI
GPT-5.1 Codex
OpenAI
1,209 50.7% 46.6s $3.44 1,931
57
Tencent
Hy3
Tencent
1,206 43.1% 166.6s $0.25 676
58
Anthropic
Claude Sonnet 4.5
Anthropic
1,204 48.2% 73.1s $6.6 21,320
59
Anthropic
Claude Opus 4.1 (Thinking)
Anthropic
1,203 56.4% 83.6s $30 7,473
60
Zhipu
GLM 4.6
Zhipu
1,202 52.8% 84.5s $0.96 14,578
61
DeepSeek
DeepSeek-V3.1 (Thinking)
DeepSeek
1,201 53.0% 166.8s $0.44 7,784
62
Anthropic
Claude Sonnet 4.5 (Thinking)
Anthropic
1,200 47.7% 73.0s $6.6 20,899
63
OpenAI
o3
OpenAI
1,200 48.1% 46.8s $3.5 590
64
Anthropic
Claude Opus 4.1
Anthropic
1,199 48.3% 85.8s $30 20,469
65
OpenAI
GPT-5.3 Codex
OpenAI
1,199 50.4% 43.5s $4.81 11,788
66
Zhipu
GLM 4.5
Zhipu
1,197 53.3% 116.5s $1 9,161
67
DeepSeek
DeepSeek-V3.2
DeepSeek
1,196 48.4% 142.6s $1 14,620
68
OpenAI
GPT-5.2 (Medium)
OpenAI
1,194 46.6% 140.5s $4.81 15,472
69
Stepfun
Step 3.7 Flash
Stepfun
1,194 44.6% 81.3s $0.44 8,165
70
DeepSeek
DeepSeek-V3.2-Exp
DeepSeek
1,190 50.6% 165.5s $0.31 9,583
71
Anthropic
Claude Sonnet 4 (Thinking)
Anthropic
1,189 55.8% 55.6s $6 7,680
72
Mistral
Mistral Medium 3.1 (2508)
Mistral
1,185 47.6% 96.2s $0.8 14,173
73
Anthropic
Claude Opus 4
Anthropic
1,183 57.9% 82.0s $30 7,932
74
Xiaomi
MiMo-V2-Flash
Xiaomi
1,178 46.1% 53.2s 16,624
75
MiniMax
MiniMax M2 Stable
MiniMax
1,178 50.0% 112.2s $0.45 5,275
76
Tencent
Hy3 Low
Tencent
1,173 39.1% 49.2s $0.25 1,187
77
Mistral
Mistral Large 3 (2512)
Mistral
1,173 45.8% 105.2s $0.75 14,978
78
Alibaba
Qwen3.5 Plus 02-15
Alibaba
1,172 44.8% 120.2s $0.59 9,623
79
OpenAI
GPT-5 mini (Default)
OpenAI
1,165 43.5% 109.2s $0.69 19,371
80
Google
Gemini 2.5 Flash Preview 09-2025
Google
1,164 48.4% 29.1s $0.85 9,097
81
Anthropic
Claude Haiku 4.5
Anthropic
1,161 45.6% 39.5s $2.2 18,482
82 1,161 41.2% 88.6s $0.17 11,320
83
Zhipu
GLM 4.7 Flash
Zhipu
1,161 45.3% 126.8s $0.15 5,798
84
Anthropic
Claude Sonnet 4
Anthropic
1,149 52.9% 60.5s $6 8,318
85
NVIDIA
Nemotron 3 Ultra
NVIDIA
1,143 36.0% 120.6s $0 4,868
86
xAI
Grok 4 Fast
xAI
1,142 42.4% 35.5s 18,019
87
Alibaba
Qwen3 Max
Alibaba
1,142 41.8% 85.3s $1.56 16,354
88
OpenAI
GPT-4.1
OpenAI
1,141 59.5% 60.3s $3.5 767
89
DeepSeek
DeepSeek-V3.1
DeepSeek
1,137 46.8% 34.2s $0.46 9,535
90
DeepSeek
DeepSeek-V3-0324
DeepSeek
1,135 51.4% 47.6s $0.63 9,090
91
Arcee Ai
Trinity Large Thinking
Arcee Ai
1,135 39.3% 70.8s $0.39 6,482
92
OpenAI
GPT-5.1 Codex Mini
OpenAI
1,134 40.6% 36.2s $0.69 17,161
93
xAI
Grok 4.1 Fast (Reasoning)
xAI
1,129 39.9% 53.8s 16,053
94
Google
Gemini 2.5 Flash Lite Preview 09-2025
Google
1,127 45.5% 9.3s 3,139
95
Prime Intellect
Prime Intellect. INTELLECT-3
Prime Intellect
1,124 38.7% 58.1s 15,077
96
Alibaba
Qwen3 Coder 30B A3B Instruct
Alibaba
1,122 54.7% 31.3s $0.12 492
97
Alibaba
Qwen3 Coder 480B A35B Instruct
Alibaba
1,120 54.9% 54.1s $0.67 902
98
xAI
Grok 4.1 Fast
xAI
1,111 37.1% 28.4s 16,318
99
OpenAI
GPT-5 nano (Default)
OpenAI
1,097 46.7% 79.7s $0.14 3,043
100
Alibaba
Qwen3-235B-A22B-Instruct-2507
Alibaba
1,095 47.7% 49.9s $0.3 3,206
101
Google
Gemini 2.5 Flash
Google
1,089 45.4% 57.6s $0.85 3,254
102
xAI
Grok 4 Fast (Reasoning)
xAI
1,085 34.7% 24.9s 18,584
103
Google
Gemini 3.1 Flash-Lite Preview
Google
1,082 33.3% 4.7s $0.56 12,910
104
xAI
Grok 4
xAI
1,076 37.0% 56.5s 11,878
105
xAI
Grok 3
xAI
1,073 39.3% 33.8s 13,192
106
OpenAI
GPT-4.1 mini
OpenAI
1,071 49.2% 73.6s $0.7 681
107
Mistral
Mistral Medium 3 (2505)
Mistral
1,069 45.7% 62.4s $0.8 2,890
108
Moonshot
Kimi K2
Moonshot
1,056 49.4% 57.0s $1 596
109
Mistral
Codestral 2508
Mistral
1,055 41.7% 12.4s $0.45 3,142
110
Alibaba
Qwen3-235B-A22B
Alibaba
1,038 41.0% 70.4s $0.8 2,399
111
OpenAI
GPT OSS 120B
OpenAI
1,037 45.1% 12.5s $0.26 2,487
112
OpenAI
o4-mini
OpenAI
1,028 50.0% 29.2s $1.93 877
113
Inception
Mercury 2
Inception
1,005 20.5% 3.0s $0.38 3,857
114
Alibaba
Qwen3 30B-A3B
Alibaba
1,005 39.0% 24.5s $0.24 1,184
115
Mistral
Devstral Medium
Mistral
986 39.8% 25.8s 3,285
116 984 32.3% 104.3s $0.75 2,908
117
OpenAI
GPT OSS 20B
OpenAI
971 39.7% 8.4s $0.08 471
118
Mistral
Mistral Small 3.2
Mistral
965 43.3% 17.0s $0.14 567
119 963 33.3% 39.6s $0.49 377
120
Allenai
Olmo 3.1 32B Think
Allenai
948 19.9% 92.5s 8,236
121
Mistral
Mistral Large 2.1 (2411)
Mistral
937 37.9% 23.4s 584
122
Meta Llama
Llama 4 Scout
Meta Llama
933 39.3% 11.7s $0.15 615
123
OpenAI
GPT-4.1 nano
OpenAI
929 41.1% 17.7s $0.18 858
124
xAI
Grok 3 Mini
xAI
928 35.5% 19.7s 3,594
125
Meta Llama
Llama 4 Maverick
Meta Llama
920 38.4% 11.0s $0.35 790
126
OpenAI
GPT-4o
OpenAI
894 36.0% 11.1s $4.38 854
127
Mistral
Codestral 2 (2501)
Mistral
817 30.8% 3.9s $0.45 702
128
Mistral
Devstral Small 1.1
Mistral
529 7.4% 5.2s 600
What this ranking means. ELO summarizes head-to-head preference results inside this category. It is useful evidence for the named task, but it remains separate from the broader Vibe Coding Index.