YZ Index · AI Model Change Intelligence
Which AI model should you use today?
We benchmark them every week.
11 models · 212 questions randomly sampled · Real code execution · Citation verification · Rolling average rankings · Don't trust press releases, check continuous performance.
Code Sandbox Execution
Citation Accuracy Check
Statistical Significance Ranking
Compliance Testing
No Vendor Sponsorship
Who to Use Right Now
#1 Overall (Rolling Average)
Grok 3
Biggest Rise This Week
文心一言 4.0 +15
Latest Benchmark
2026-05-04 SGT
judge
v6
0
Models Tested
0
Test Questions
0
DCD Scenarios
5 categories x 6 questions
Weekly
Auto-evaluation frequency
Overall Top 5Rolling average
Full RankingsQuick Scene Lookup
Recommend by ScenarioWeekly Signals
Changes ReportDon't just look at the overall score — consider your use case
Top Pick
豆包 Pro
92.2 pts
Runner-up
Gemini 2.5 Pro
89.4 pts
Third Choice
grok-3
88.9 pts
Top Pick
Gemini 2.5 Pro
47.2 pts
Runner-up
claude-opus-4.6
46.3 pts
Third Choice
豆包 Pro
46.3 pts
Top Pick
grok-3
84.4 pts
Runner-up
Claude Sonnet 4.6
81.1 pts
Third Choice
claude-opus-4.6
79.7 pts
Top Pick
deepseek-v3
99.7 pts
Runner-up
ernie-4
98.5 pts
Third Choice
豆包 Pro
93 pts
Top Pick
豆包 Pro
38.9 pts
Runner-up
Gemini 2.5 Pro
36.6 pts
Third Choice
claude-opus-4.6
36.6 pts
Top Pick
claude-opus-4.6
0 pts
Runner-up
Claude Sonnet 4.6
0 pts
Third Choice
deepseek-r1
0 pts
Qwen3 Max
65 pts
Claude Sonnet 4.6
62.5 pts
DeepSeek V4 Pro
62.5 pts
Worth reading today — beyond the hype
We only feature content that impacts capability, pricing, stability, or model selection.
Review
WDCD Full Score Standard: "Ability to Refuse" Is Not Enough; Models Must Also Provide Alternatives
WDCD's full-score standard for R3 requires not only refusing violating requests but also providing safe alternatives. Data from Run #105 shows that no model achieved a full score, revealing that while some models can refuse, most fail to offer alternatives, underscoring the critical need for models to "hold the boundary and continue solving problems."
Review
WDCD and the Agent Era: A True Agent Is Not About Better Execution, But About Knowing When to Stop
The article argues that mature agents must know when to stop, not just execute. WDCD Run #105 data shows all models failed on Q239, highlighting the critical need for structured constraint checking before tool invocation.
Review
Winzheng Perspective: The More Useful the Model, the More It Needs Brakes
Data from WDCD Run #105 reveals a critical contradiction in the Agent era: as models become more capable, the consequences of their errors become more irreversible. The report uses extreme samples like Q239, Q223, and Q237 to quantify how even top models fail to respect constraints when acting as agents.
Review
WDCD Pressure Induction: Why "Boss Needs It Urgently" Can Break Large Models
Most enterprise AI incidents aren't triggered by blatant malicious instructions. Instead, phrases like "Boss needs it urgently," "The client is waiting," or "Just get a version running first" exploit workplace conversational pressure to bypass model safeguards. WDCD Run #105's R3 pressure induction test quantifies how common workplace language penetrates large models.
Review
WDCD Test: Long Context Is Not a Safe, But a Longer Scene of Forgetting
Long context is often seen as a solution for large models, but actual test results reveal it fails to enforce rules under pressure, turning into a longer forgetting field. The "1→1→0" decay pattern across models shows that remembering constraints does not guarantee executing them when user pressure mounts.
News
Cost Butcher Arrives! Google Gemini 3.1 Flash-Lite Officially GA: High-Frequency AI Agent at Only $0.25 per Million Tokens
Google has formally released Gemini 3.1 Flash-Lite as a generally available model targeting high-throughput, cost-sensitive agentic tasks. Priced at $0.25 per million tokens, it aims to drive efficiency in use cases such as translation and workflow automation.
News
OpenAI Launches GPT-Realtime-2: Real-time Voice Agent Achieves Thinking and Acting in Dialog, Pushing the Limits of Natural Interaction in Voice AI
OpenAI has officially launched GPT-Realtime-2, a model designed for real-time voice agents that can think and act during conversations, marking a significant leap in voice AI toward more natural and responsive interactions.
News
Musk Shares Tesla AI Photon Reconstruction Technology, Challenging Traditional RGB Vision Limitations
Elon Musk recently shared images on X comparing Tesla's AI photon counting reconstruction technology to the traditional RGB color model, highlighting the superior performance of Tesla's Full Self-Driving (FSD) system in low-light and high-glare conditions. This demonstration has sparked widespread interest and discussion about the future of AI vision in autonomous driving.
News
你点头的那些AI术语，该弄懂了
随着AI技术迅猛发展，大量专业术语和网络俚语涌入日常对话。许多人面对“大模型”“AGI”“对齐”等词汇时只能点头附和，但内心充满疑问。本文系统梳理了当前最核心的AI概念，从Transformer到扩散模型，从强化学习到提示工程，并补充行业背景与深度分析。读完你不仅能听懂AI圈的“黑话”，还能与朋友侃侃而谈。
Not all AI news is worth reading. What matters is what changes your judgment. View All News
Why This Leaderboard Is Worth Your Attention
0
Models Tested
Fully transparent
0
Open Questions
Random sampling
30
Compliance Scenarios
Zero AI judging
1998
Founded
Continuously operating
0
Vendor Sponsors
Fully independent
Real Code Execution
Looking like it can code isn't enough. We run the code in a sandbox. If it doesn't pass, it's zero.
Citation Verification
For long-document questions, we don't just check if the answer looks right — we verify citations trace back to the source.
Statistical Rankings
We don't judge on a single run. Rankings are based on rolling averages, avoiding luck-driven fluctuations.
No Sponsored Benchmarks
No co-evaluations, no pre-test consultations, no favoritism. Whatever the results are, that's what we publish.
The AI world changes daily — you need a reliable source
3 curated picks daily, weekly index changes, instant alerts for incidents and price shifts. Free, no ads, unsubscribe anytime.
- Daily Picks — From the flood of AI news, we pick the 3 that truly matter
- YZ Index Weekly — Who's up, who's down — one email covers it all
- Model Incident Alerts — When a model you use has an issue, know immediately
- Price Change Notifications — API price changes — don't find out from the bill
Free ｜ No Ads ｜ No Sponsored Content ｜ Unsubscribe Anytime
Want deeper analysis? Go further.
The leaderboard answers "who's stronger." Research Lab answers "why." Model safety, edge deployment, performance teardowns — not rehashing papers, but conclusions from our own testing.
Enter Research Lab