Skip to main content
YZ Index

Winzheng · Grounding Rankings

Long document citation verification and grounding accuracy.

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

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