Latest

Every published item, in order · 9305 items
Oct 15
ModelsBuildersMulti-sourceSelected12:57
Claude Opus 5.5 and Grok 4.7 recall Eiffel Tower names in 3D test

The result measures long-tail factual recall plus 3D generation quality in a single offline benchmark, a combination few evals test. Builders comparing frontier models on spatial reasoning and world knowledge can use the same sandboxed prompt setup for their own side-by-side runs. Claude Opus 5.5 (Anthropic) edged out Grok 4.7 (xAI) on geographic accuracy of the name placement.

Event
Official accountArtificial Analysis@ArtificialAnlysSource
ModelsBuildersMulti-sourceSelected71°12:54
AMD MI355X joins AA-AgentPerf benchmark against NVIDIA Blackwell

The MI355X's 288GB of HBM3E per GPU gives it an edge on very large models like the 1.6T-parameter DeepSeek V4 Pro, but serving-stack maturity on ROCm remains the bottleneck at higher loads. Teams evaluating accelerator purchases for agentic inference can now compare AMD and NVIDIA on realistic coding-agent workloads rather than synthetic throughput numbers. All results run on ROCm nightly builds of vLLM and SGLang, so scores should improve as the software stack matures.

Event
Official accountArtificial Analysis@ArtificialAnlysSource
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
ModelsBuildersSelected12:53
Meta releases Muse Wonder and Muse Wonder Full agent models

Meta entering the agentic model space puts it in direct competition with OpenAI's operator-style agents and Anthropic's computer-use models, rather than just chat assistants. Developers building personal-assistant or workplace automation products should read the researcher blog to compare benchmark scores against their current agent stack before choosing a base model.

Official accountMeta AI@AIatMetaSource
ModelsUS vs ChinaMulti-sourceSelected12:46
Paper Instruments releases Ultramarine 1 Flash for document workloads

A cost gap of roughly 60x per task against Claude Fable 5, while scoring higher on a deliverables benchmark, could push professional-services firms to re-evaluate which workloads run on open models. Builders fine-tuning on top of GLM-5.3 Flash now have a concrete vertical example of post-training for rubric-graded outputs. Its open weights also make on-premise deployment viable for firms with client confidentiality constraints.

Event
TestingCatalog@testingcatalogSource
ModelsBuildersSelected12:37
Stanford team's Next-Concept Modeling generates text 10-31x faster

The result suggests the next speed leap may come from changing generation granularity rather than from bigger GPUs: drafting concepts first, then filling in tokens. Researchers and engineers comparing sampling strategies for diffusion and autoregressive models can benchmark NCM against baselines like diffusion language models using far fewer training tokens. As it comes from the Stanford Hazy Research group, expect open follow-ups and code to appear in the open-source model ecosystem.

Event
Stanford AI Lab@StanfordAILabSource
ModelsUS vs ChinaSelected12:34
Epoch AI Launches SpireClimb Benchmark for Slay the Spire

Progress on a single long-horizon game is a proxy for how quickly agentic planning and decision-making capabilities are moving, and SpireClimb gives teams a repeatable way to measure that gap across model releases. Practitioners benchmarking agents on sequential decision tasks can use the difficulty tiers to compare models beyond static Q&A tests. Tracking which labs' models clear the hardest difficulty will be a useful signal in coming releases.

Official accountEpoch AI@EpochAIResearchSource
ModelsBuildersSelected09:41
CRIS-0 agent generates its own robot positioning functions from demos

The notable shift is self-repair: instead of a fixed pipeline, the robot's manipulation code improves itself each time execution fails, so errors become training signal without human relabeling. Practitioners working on robot manipulation or agentic tool-building can study how error messages drive function patching in a physical loop. Compared with SAM2, pairing SAM3 with RGB-D gives this setup grounding in real 3D workspaces.

Aran Komatsuzaki (论文推介)@arankomatsuzakiSource

Only the latest 2000 items are listed; for older ones see the daily archive