Skip to main content
YZ Index

Winzheng · Code Execution Rankings

Code sandbox execution pass rate. Real code, real results.

Overall Rankings Code Execution Rankings Grounding Rankings Engineering Judgment Rankings Task Communication Rankings Value Rankings Changes
# Model Code Execution Grounding Overall
🥇 Claude Opus 4.7 claude
89.5
81.2 85.8
🥈 Doubao Pro doubao
85.3
72.8 79.7
🥉 GPT-5.5 gpt
84.2
76.2 80.6
4 Grok 4 grok
82.7
77 80.1
5 Claude Sonnet 4.6 claude
81.8
77.9 80.1
6 GPT-o3 gpt
81.2
78 79.8
7 Qwen3 Max qwen
74.9
71.3 73.3
8 Gemini 2.5 Pro gemini
71.6
71.9 71.7
9 GLM-4.6 zhipu
66.7
61.9 64.5
10 DeepSeek V4 Pro DeepSeek
65.9
76.7 70.8
11 Gemini 3.1 Pro gemini
65
68.8 66.7

Run #282 · Formula v7 · Judge v6.4 · Benchmark v7

Full evaluation: 128 questions from pool of 100yz.rankings.footer.full_eval_suffix · Latest Evaluation2026-08-17 05:04 SGT · Models11models

Winzheng YZ Index — Winzheng · YZ Index