Skip to main content
YZ Index

Winzheng · Engineering Judgment Rankings

Architecture review, risk assessment, engineering decision-making.

Overall Rankings Code Execution Rankings Grounding Rankings Engineering Judgment Rankings Task Communication Rankings Value Rankings Changes
Side Dimension Rankings — Communication + Judgment sub-dimension performance
# Model Engineering Judgment Code Execution Overall
🥇 Doubao Pro doubao
90
82.9 75.7
🥈 GPT-5.5 gpt
87.8
88.3 79.1
🥉 Claude Sonnet 4.6 claude
83.8
76.3 74.7
4 GPT-o3 gpt
82.6
86 81.7
5 Claude Opus 4.7 claude
82.5
85.7 82.6
6 Gemini 3.1 Pro gemini
77.8
71.2 69.3
7 DeepSeek V4 Pro DeepSeek
72.8
69.7 71.6
8 Grok 4 grok
63.2
83.3 77.2
9 Gemini 2.5 Pro gemini
58.9
75.5 73.2
10 Qwen3 Max qwen
41.7
76.9 71.6
11 GLM-4.6 zhipu
23.1
65.2 64

Run #313 · Formula v7 · Judge v6.4 · Benchmark v7

Full evaluation: 128 questions from pool of 100yz.rankings.footer.full_eval_suffix · Latest Evaluation2026-09-07 05:06 SGT · Models11models

Winzheng YZ Index — Winzheng · YZ Index