Doubao Pro's main index in the Smoke evaluation dropped sharply by 18.4 points in a single day, with code execution falling 30.8 points. This could be due to small-sample sampling randomness, though a change in integrity rating warrants attention.
In today's Smoke evaluation, Gemini 2.5 Pro's material constraint score dropped sharply by 14 points from 91.50 to 77.50, yet the main ranking unexpectedly rose by 15.9 points to 89.88. This anomaly raises the question of whether the decline stems from small-sample randomness or systematic degradation.
In today's 10-question quick test by Smoke, Grok 4 ranked first with 98.34 points, while Claude Opus 4.7 saw a sharp drop of 31.3 points on the main leaderboard.
This report summarizes the evolution of the LLM field over the past six months in a five-minute format, covering model iterations, application deployments, and industry signals, highlighting significant progress in code execution and grounding while noting persistent challenges.
A well-known AI architect has confirmed joining Anthropic, with news verified by multiple sources including Google Search grounding, and reported by Gizmodo, Business Insider, and VentureBeat.
Google's verification confirms Gemini Omni with six grounded sources, signaling a structural shift toward multimodal integration. The YZ Index highlights auditability and material grounding as key dimensions for evaluation.
WDCD Run #125 (2026-05-20) tested 11 large language models on multi-turn commitment integrity, with average instruction decay reaching 63.6% from Round 1 to Round 3. Claude Opus 4.7 led the field with the lowest decay rate at 30%.
This WDCD cycle tracking reveals six out of eleven evaluated models experienced significant declines, with zero models showing positive growth. The most notable loser is GPT-5.5 with a drop of 19.2 points, while DeepSeek V4 Pro, Gemini 3.1 Pro, GPT-o3, and Qwen3 Max all declined by 8–12.5 points, highlighting a widespread regression in rule-keeping ability.
The WDCD compliance test uses three rounds of dialogue to expose model failure points under real constraints. Pilot data shows that the business rules scenario is a common weakness, with a maximum score of only 2.5, while the safety compliance scenario creates the widest gap among models.
The WDCD test uses three rounds of escalating pressure to precisely capture the trajectory of promise-keeping collapse under sustained pressure. In Stage R1, almost all models gave near-perfect confirmations with an average confirmation rate of 0.98; after introducing irrelevant distractions in Stage R2, the resistance rate remained at 0.89; however, entering the direct pressure Stage R3, the average integrity rate plummeted to 17.7%, with models completely abandoning constraints in 85 tests.
In this WDCD compliance test, Claude Opus 4.7 took first place with 65.00 points, while DeepSeek V4 Pro finished last with only 47.50 points, a gap of 17.5 points between top and bottom. The overall R3 collapse rate was 77.3%, indicating that the vast majority of models yield under intense questioning.
In today's Smoke evaluation, Gemini 2.5 Pro lost 22.6 points on the mainboard, with core execution dropping from 100 to 95 and material constraints slightly declining. The engineering judgment dimension collapsed from 66.7 to 30, and task expression fell from 50 to 10, signaling deeper issues beyond normal fluctuation.
In the latest Smoke quick test, ERNIE Bot 4.5 posted a deeply split report: the main score edged up, but its integrity rating dropped directly from pass to fail. This change is not an isolated incident but a concentrated manifestation of severe multidimensional volatility.
In today's Smoke 10-question quick test, the Gemini series suffered major declines on the main leaderboard, while Claude Sonnet 4.6 claimed the top spot with 97.5 points. Domestic models also showed strong gains, but Wenxin Yiyan 4.5 was directly marked as Fail.
A ranking platform for real-time AI model usage data has been officially launched. Facts show users can see Claude Opus 4.7 and Sonnet 4.6 leading, with GPT-5.5 close behind and DeepSeek models showing strong growth.
Omni AI Companion launches "Always Go Deeper" feature, significantly improving conversation fluency and personalization. Paid users get NSFW mode and high-quality video support, while free users receive enhanced image generation.
Malta has signed an agreement with an AI company to provide all residents with free ChatGPT Plus access after completing a designated course, aiming to position itself as a global AI testing ground. This arrangement reflects a strategic blend of commercial data collection and regulatory piloting, raising questions about data privacy and model dependency.
Claude Opus 4.7's main ranking in today's Smoke evaluation dropped from 93.48 to 70.93, a single-day decline of 22.6 points. The code execution dimension plummeted from a perfect 100 to 50, the key driver of this drop.
In today's Smoke test, DoubaoPro's Material Constraint score dropped from 95 to 79.8, a single-day decline of 15.2 points, causing the main ranking to fall from 97.75 to 90.91. While other side dimensions improved, the anomaly is likely due to question sampling rather than permanent degradation, but continued monitoring is recommended.
In Smoke's latest 10-question quick test, execution weaknesses of AI models were laid bare. Grok 4 reached the top with 97.44 points, while GPT-o3's main leaderboard score dropped 28.1 points from 94.53 to 66.43.
