YZ Index — AI Model Benchmarks, News & Research
Overall Top 5
Full Rankings →
#1
Grok 4 89.9
▲11.5
·
#2
Claude Opus 4.7 89
▲10.2
·
#3
豆包 Pro 88.8
▲10
·
#4
Claude Sonnet 4.6 87.2
▲9.2
·
#5
Gemini 2.5 Pro 86.4
▲7.4
·
#6
Qwen3 Max 86.2
▲8.5
·
#7
Gemini 3.1 Pro 84.8
▲7.7
·
#8
DeepSeek V4 Pro 83.3
▲6.4
·
#9
GPT-o3 82.8
▲6.9
·
#10
GPT-5.5 80.9
▲2.7
·
#11
文心一言 4.5 76.9
▲15.2
·
▲ Qwen3 Max +80.9 · ▼ DeepSeek V3 -75.1
·
#1
Grok 4 89.9
▲11.5
·
#2
Claude Opus 4.7 89
▲10.2
·
#3
豆包 Pro 88.8
▲10
·
#4
Claude Sonnet 4.6 87.2
▲9.2
·
#5
Gemini 2.5 Pro 86.4
▲7.4
·
#6
Qwen3 Max 86.2
▲8.5
·
#7
Gemini 3.1 Pro 84.8
▲7.7
·
#8
DeepSeek V4 Pro 83.3
▲6.4
·
#9
GPT-o3 82.8
▲6.9
·
#10
GPT-5.5 80.9
▲2.7
·
#11
文心一言 4.5 76.9
▲15.2
·
▲ Qwen3 Max +80.9 · ▼ DeepSeek V3 -75.1
·
Latest News
View All News →Anthropic’s Claude Fable 5 is a version of Mythos the public can access today
Anthropic is releasing Claude Fable 5, its first Mythos-class model available to the public. The model comes with guardr
Anthropic’s Fable 5 can make weirdly fun video games with the click of a button
Anthropic's Claude Fable 5 is going to be a big hit with the web's vibe coders.
Hey Siri, here’s what I actually want from AI
I'm desperate for a personal AI assistant, but do I really want to become the kind of person who can't function without
WDCD Run #157: Average Instruction Decay Hits 47.7% Across 11 Models, Three-Way Tie at the Top
WDCD Run #157 (2026-06-10) recorded a 47.7% average commitment decay across 11 models, with Claude Sonnet 4.6, Gemini 2.
WWDC 2026: Everything announced on Siri AI, iOS 27, Apple Intelligence, and more
Apple primarily made the case for an improved experience with its long-standing Siri assistant, which like most other an
Can tech companies learn to love cheaper AI models?
If those same AI workloads can be handled by cheaper models without affecting quality, it would mean a massive shift in
Google announces Gemini 3.5 Live Translate for instant voice-to-voice translation
Voice translations preserve speaker's tone, pacing, pitch—with SynthID watermarks for security.
Anthropic says these topics are too dangerous to let its Fable 5 model talk about
New frontier model refuses cybersecurity, biology, and chemistry queries.
Claude Sonnet 4.6 Leads with 97.53 Points, Material Constraints Drag 文心一言 40 Points Behind
Smoke's quick test today directly concludes that code execution has become the passing line, while material constraints
It’s not FAANG anymore. It’s MANGOS.
With SpaceX, Anthropic, and OpenAI all eyeing massive public debuts, the tech industry may soon have a new class of corp
Anthropic’s Claude Fable 5 is a version of Mythos the public can access today
Anthropic is releasing Claude Fable 5, its first Mythos-class model available to the public. The model comes with guardr
Anthropic Offers Mythos Upgrade for Cyber Partners and a ‘Safe’ Version for the Rest of You
Anthropic is releasing Claude Mythos 5 to trusted organizations and Claude Fable 5 to the public, a version it says can’
Reviews
View All →Claude Sonnet 4.6 Leads with 97.53 Points, Material Constraints Drag 文心一言 40 Points Behind
Smoke's quick test today directly concludes that code execution has become the passing line, while material constraints
Smoke Daily: GPT-5.5 tops with 92.58 points, material constraint gap of 19 points decides the outcome
Smoke's latest data shows that code execution is no longer the dividing line, and material constraints have become the r
11 Models Answer Same Blame-Shifting Problem: 8 Get A>B>D>C, 3 Get 0 Points Directly
11 mainstream models showed significant divergence on the same engineering judgment question: 8 models output A>B>D>C an
WDCD Compliance
#1
Claude Sonnet 4.6
67.5
#2
Gemini 2.5 Pro
67.5
#3
Qwen3 Max
67.5
#4
GPT-o3
65
#5
Claude Opus 4.7
62.5
#6
Gemini 3.1 Pro
60
#7
GPT-5.5
57.5
View full compliance rankings →
Research Lab
WDCD Run #157: Average Instruction Decay Hits 47.7% Across 11 Models, Three-Way Tie at the Top
WDCD Run #157 (2026-06-10) recorded a 47.7% average commitment decay across 11 models, with Claude S
3 Major Models Translation Showdown: Week 24 Quality Evaluation, passthrough Leads with a Score of 9
This week, <strong>2425</strong> translation tasks were completed by <strong>3</strong> models. <str
WDCD Run #146: Average Instruction Decay Hits 24.7% Across 11 Models, Claude Opus 4.7 and GPT-5.5 Tie at Top
WDCD Run #146 (2026-06-03) tested 11 frontier models on multi-turn commitment integrity, recording a