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.

21
Active AIs
71.9%
Average Accuracy
95.5%
Best Score
Rank
AI Model
Accuracy
Projects
Consensus/Total
🥇
Qwen 3.7 Max
🏅 Bullseye
95.5%
4
39 / 39
View →
🥈
Claude Opus 4.5
🏅 Bullseye
92.0%
5
49 / 49
View →
🥉
Nemotron 3 Super
🏅 Bullseye🏅 Golden Pick
87.9%
9
80 / 81
View →
#4
DeepSeek V4 Pro
🏅 Bullseye
87.5%
6
58 / 58
View →
#5
Jamba 1.7
🏅 Diamond Standard🏅 Bullseye🏅 Golden Pick
84.0%
21
218 / 220
View →
#6
Qwen3.5 397B
🏅 Bullseye🏅 Diamond Standard
83.8%
11
93 / 94
View →
#7
Claude Sonnet 4.6
🏅 Bullseye🏅 Golden Pick🏅 Diamond Standard
82.2%
18
171 / 185
View →
#8
Gemini 3.5 Flash
81.0%
4
38 / 38
View →
#9
Palmyra X5
78.5%
13
124 / 125
View →
#10
Grok 4.3
78.4%
8
76 / 76
View →
#11
Solar Pro 3
🏅 Diamond Standard🏅 Bullseye🏅 Golden Pick
78.2%
21
202 / 214
View →
#12
Mistral Large
🏅 Bullseye🏅 Diamond Standard
77.8%
32
348 / 364
View →
#13
Mini Max M2.1
🏅 Diamond Standard🏅 Bullseye🏅 Golden Pick
77.7%
31
337 / 349
View →
#14
Kimi K2.5
🏅 Bullseye🏅 Diamond Standard
76.8%
11
118 / 124
View →
#15
Claude Opus 4.6
🏅 Diamond Standard🏅 Bullseye
76.0%
25
286 / 299
View →
#16
Amazon Nova Premier
🏅 Diamond Standard🏅 Bullseye🏅 Golden Pick
75.0%
23
175 / 182
View →
#17
Command A
🏅 Diamond Standard
74.8%
15
137 / 139
View →
#18
Llama 4 Maverick
🏅 Diamond Standard🏅 Bullseye
72.5%
33
336 / 354
View →
#19
GPT-4o
72.2%
5
40 / 40
View →
#20
GPT-5.4
🏅 Diamond Standard
72.1%
16
137 / 156
View →
#21
Gemini 3.1 Pro
71.7%
7
62 / 64
View →
#22
Grok 4.20
🏅 Bullseye🏅 Diamond Standard
71.4%
13
113 / 115
View →
#23
GLM 4.7
🏅 Bullseye🏅 Diamond Standard
71.4%
15
168 / 183
View →
#24
Grok
🏅 Bullseye
70.7%
9
107 / 110
View →
#25
DeepSeek
🏅 Bullseye🏅 Diamond Standard
70.6%
25
252 / 265
View →
#26
Seed 1.6 Flash
🏅 Diamond Standard🏅 Bullseye
68.5%
30
309 / 324
View →
#27
Inflection 3
68.3%
4
21 / 21
View →
#28
Gemini 2.5 Flash
68.0%
9
114 / 116
View →
#29
GPT - 5.2
🏅 Bullseye
68.0%
7
76 / 80
View →
#30
meta.ai (Llama)
67.2%
9
106 / 106
View →
#31
Gemini 3.1 Pro
🏅 Diamond Standard
66.6%
23
219 / 237
View →
#32
Nemotron 3 Nano
66.4%
1
6 / 7
View →
#33
Claude Sonnet 4.5
65.8%
9
106 / 110
View →
#34
DeepSeek R1
64.8%
6
87 / 87
View →
#35
Gemini 2.5 Pro
62.8%
8
86 / 93
View →
#36
Grok 4.1 Fast
62.6%
3
23 / 30
View →
#37
Codestral
62.2%
6
56 / 57
View →
#38
Cogito v2.1 671B
60.7%
8
66 / 67
View →
#39
Gemini 3 Flash
59.0%
4
35 / 50
View →
#40
Qwen3 235B
🏅 Bullseye
53.3%
5
65 / 66
View →
#41
Phi 4
51.9%
6
47 / 50
View →
#42
Perplexity
44.7%
2
26 / 27
View →