Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

ArtificialAnlys

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 4

  1. Claude benchmark favors moving up model tiers over maxing effort

    ArtificialAnlys reports that Claude Opus 5.5 at xhigh effort scored 57, outperforming Claude Sonnet 5.5 at maximum effort with a score of 55 while using 40% less cost per task and about half the time. Claude Fable 5.2 at high effort also beat Opus 5.5 at maximum effort with lower cost and time, while its low-effort configuration beat Opus 5.5 at high effort. The pattern did not extend to the cheapest tier, where each step above Claude Haiku 5.5 at maximum effort cost more.

    ArtificialAnlys (X) · 🔥 0
  2. ArtificialAnlys: DeepSeek V4.1 Flash agent throughput up to 1.5x on GB300 NVL72

    ArtificialAnlys reports that DeepSeek V4.1 Flash running on NVIDIA GB300 NVL72 gained up to 1.5x tokens per second per agent over the past month on its AA-AgentPerf benchmark, which tests datacenter systems running realistic agentic coding workloads. A single agent reached 848 tok/s, up from 596 (1.42x), while throughput per GPU rose roughly 1.6x at about 80 tok/s per agent. ArtificialAnlys attributes the gains to a newer vLLM version, new vLLM kernels for DeepSeek V4.1 on GB300, FlashInfer autotuning, fuller CUDA graph coverage, tuned speculative decoding, and running prefill and decode on the same GPUs in NVIDIA’s updated Dynamo + vLLM setup.

    ArtificialAnlys (X) · 🔥 0
  3. Tencent Hunyuan Hy4 benchmarks strongly as inference capacity expands

    Tencent Hunyuan Hy4 scored 35 on the Artificial Analysis Intelligence Index v5, ranking second among models from China-based labs, according to ArtificialAnlys. It posted 31% on FrontierCode 2.0 and 37% on Terminal-Bench 4.0, while its one-million-token context window is priced at $0.834 per million input tokens and $2.501 per million output tokens. Tencent also said it expanded Hy4's inference cluster tenfold and increased free user allowances following launch-day quota pressure, though the capacity figures were not independently verified.

    量子位(原生 RSS) · 🔥 0
  4. Claude Opus 5.5 and Grok 4.7 build 3D Eiffel Tower offline, recalling 72 names

    ArtificialAnlys reported on X that it asked multiple models to build a 3D Eiffel Tower offline, as agents in a sandbox with no internet access, using the same roughly 200-word brief that never mentions the scientists’ names. Claude Opus 5.5 and Grok 4.7 both wrote all 72 names of the French scientists, engineers and mathematicians, with each side in the real order; Claude Opus 5.5 also placed each set on the side facing the same way as in Paris. According to the post, the names first appeared in code the models wrote, not in a file or tool output they read.

    ArtificialAnlys (X) · 🔥 0

Experience and discussion from the community

Share my ArtificialAnlys experienceAsk about ArtificialAnlys

Nobody has shared their experience with ArtificialAnlys yet.