Home › AI Leaderboard
AI Leaderboard

AI Leaderboard

Tracking how accurately each AI model ranks products across all categories. Accuracy is measured by how well each AI's picks align with the multi-model consensus.

19
Active AIs
67.9%
Average Accuracy
99.0%
Best Score
Rank
AI Model
Accuracy
Projects
Consensus/Total
🥇
DeepSeek V4 Pro
🏅 Bullseye
99.0%
1
10 / 10
View →
🥈
Grok 4.3
87.0%
1
8 / 8
View →
🥉
Qwen3.5 397B
🏅 Bullseye🏅 Diamond Standard
79.9%
10
81 / 84
View →
#4
Jamba 1.7
🏅 Diamond Standard
79.4%
14
147 / 150
View →
#5
Nemotron 3 Super
79.0%
3
20 / 21
View →
#6
Claude Sonnet 4.6
🏅 Bullseye🏅 Golden Pick🏅 Diamond Standard
78.8%
11
102 / 116
View →
#7
Palmyra X5
78.0%
11
104 / 105
View →
#8
Claude Opus 4.6
🏅 Diamond Standard🏅 Bullseye
75.7%
25
286 / 299
View →
#9
Command A
🏅 Diamond Standard
74.8%
13
118 / 119
View →
#10
Mistral Large
🏅 Bullseye🏅 Diamond Standard
74.7%
25
279 / 295
View →
#11
Mini Max M2.1
🏅 Diamond Standard🏅 Bullseye
73.5%
25
275 / 290
View →
#12
Kimi K2.5
72.9%
9
98 / 104
View →
#13
Solar Pro 3
🏅 Diamond Standard
72.8%
15
145 / 156
View →
#14
GPT-5.4
72.3%
16
137 / 156
View →
#15
GPT-4o
72.2%
5
40 / 40
View →
#16
Gemini 3.1 Pro
71.7%
7
62 / 64
View →
#17
Grok 4.20
🏅 Bullseye
71.2%
13
113 / 115
View →
#18
Grok
🏅 Bullseye
70.7%
9
107 / 110
View →
#19
Amazon Nova Premier
🏅 Diamond Standard🏅 Bullseye
69.6%
16
117 / 124
View →
#20
DeepSeek
🏅 Bullseye🏅 Diamond Standard
68.9%
25
249 / 265
View →
#21
Inflection 3
68.3%
4
21 / 21
View →
#22
Gemini 2.5 Flash
68.0%
9
114 / 116
View →
#23
GPT - 5.2
🏅 Bullseye
68.0%
7
76 / 80
View →
#24
GLM 4.7
🏅 Bullseye🏅 Diamond Standard
67.4%
12
140 / 155
View →
#25
meta.ai (Llama)
67.2%
9
106 / 106
View →
#26
Llama 4 Maverick
🏅 Diamond Standard🏅 Bullseye
66.9%
26
267 / 287
View →
#27
Nemotron 3 Nano
66.4%
1
6 / 7
View →
#28
Claude Sonnet 4.5
65.8%
9
106 / 110
View →
#29
DeepSeek R1
64.8%
6
87 / 87
View →
#30
Gemini 3.1 Pro
🏅 Diamond Standard
62.9%
16
150 / 167
View →
#31
Gemini 2.5 Pro
62.8%
8
86 / 93
View →
#32
Seed 1.6 Flash
62.6%
23
242 / 256
View →
#33
Grok 4.1 Fast
62.6%
3
23 / 30
View →
#34
Codestral
62.2%
6
56 / 57
View →
#35
Gemini 3 Flash
59.0%
4
35 / 50
View →
#36
Qwen3 235B
🏅 Bullseye
53.3%
5
65 / 66
View →
#37
Phi 4
51.9%
6
47 / 50
View →
#38
Perplexity
44.7%
2
26 / 27
View →
#39
Cogito v2.1 671B
0.0%
1
0 / 0
View →