YZ Index
Model Profiles
Click a model to view detailed performance data
豆包 Pro
doubao
78.3
#1 / 11
Code Execution leader,Communication top tier,Most stable
DeepSeek V3
DeepSeek
74.8
#2 / 11
Communication top tier,Best value,High availability
文心一言 4.0
ernie
72.0
#3 / 11
Communication top tier,High availability
DeepSeek R1
DeepSeek
70.0
#4 / 11
Communication top tier,High availability
Gemini 2.5 Pro
gemini
69.7
#5 / 11
Judgment leader,Communication top tier,High availability
Grok 3
grok
67.7
#6 / 11
Overall #1,Grounding leader,Communication top tier
Claude Sonnet 4.6
claude
66.2
#7 / 11
Communication top tier
Qwen Max
qwen
65.4
#8 / 11
Communication top tier,High availability
Claude Opus 4.6
claude
62.8
#9 / 11
Communication top tier,High availability
GPT-4o
gpt
57.2
#10 / 11
Communication top tier
GPT-o3
gpt
51.5
#11 / 11
Communication top tier