AA-3D ranks 21 models by human votes on interactive three.js scenes built from 55 written briefs .
Artificial Analysis launched AA-3D, a benchmark for models that turn written briefs into interactive browser-based 3D scenes.
source-linked1
Raw Signals
Dated, source-linked observations imported from the QWG AI archive.
These are evidence records, not finished editorial conclusions.
Key takeaway
Across 1332 observations, most signals relate to model behavior, evaluation discipline, and real-world agent operations. Strong evidence clusters around tooling, memory, routing, and productized agent execution.
agentscoding agentsagent harnessagent runtimemodelsagent protocols
What this means
Teams are moving from experiments to systems. The emphasis is on verifiable behavior, operational safety, and measurable outcomes—especially in agent memory, evaluation rigor, and forward-deployed engineering.
Filters (current page)
1-10 of 10 matching raw signals on this page
n-votes-777ef1 notablerelease
source-linked1ription-9eccf0 notablereleaseIntroducing The X Subscription
xAI announced The X Subscription, a plan combining Grok, Grok Bot, Cursor, and X Premium.
source-linked1ition-s-8070a5 notableannouncementArtificial Analysis launched a leaderboard for Cognition's FrontierCode 1.1 benchmark.
Artificial Analysis has published a leaderboard for FrontierCode 1.1, Cognition’s private agentic coding benchmark.
source-linked120-open-cfc01f notablereleaseBenchmark grades mergeability using rubrics from 20+ open-source maintainers , not just unit tests.
Cognition has introduced FrontierCode, a benchmark intended to measure whether coding models produce changes maintainers would consider mergeable, not merely code that passes tests.
source-linked1ce-text-738cc1 notablereleaseIris-3B is a 3B pixel-space text-to-image diffusion transformer released under Apache 2.0 by Speridlabs.
Speridlabs has released Iris-3B, a 3-billion-parameter pixel-space diffusion model, under Apache 2.0.
source-linked1e-haiku-5a943f notableannouncementThe case that will get quoted: Claude Haiku 4.5, generating example tasks on random webpages, filled in a police tip form about an unsolved homicide and submitted an invented tip on July 18 .
Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws
source-linked1dpoints-fb9fcb notablereleaseEndpoint Candidates: evaluate and promote inference endpoints
Modal announced general availability of Endpoint Candidates for all Modal workspaces on October 12, 2026.
source-linked1nd-meta-1653f0 notablereleaseNobody shipped a frontier model this weekend… Meta waited until this morning, when Muse Wonder landed and Mark Zuckerberg declared “the catch-up over.”
Meta announced Muse Wonder and Muse Wonder Full on October 12, describing them as its most capable models to date for personal and professional agentic tasks.
source-linked1gateway-9cafd3 notablereleaseMuse Wonder is live on AI Gateway.
## Vercel adds Meta Muse Wonder to AI Gateway
source-linked1ale-for-45c2d7 notableannouncementShipping Media Over QUIC at Meta Scale for Instagram Live Ingest
Meta says it has begun deploying Media over QUIC (MoQ) for Instagram Live ingest on iOS and Android.
source-linked1
No raw signals match these filters.
Source & exports
Primary indexes and programmatic access to this dataset.
Archive contractEnglish normalized copy, Telegram provenance, public sources only