#kernelbench
Live, measured metrics for the hashtag #kernelbench from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #kernelbench
This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.
Day-by-day usage
measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 21:53 UTC0 uses by 0 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-27 21:53 UTCNo related tags with measured usage found for #kernelbench.
Live pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 21:53 UTCEverything below is measured over the latest 2 public posts (spanning ~690 hours).
Posting hours (UTC)
Languages: English (1) · German (1)
Avg boosts / post: 0
Top of the latest posts
Rohan Paul (@rohanpaul_ai) Kimi K3가 KernelBench에서 H100용 CUDA 커널을 생성해 최적화된 PyTorch 구현보다 최대 14.82배 빠른 성능을 냈으며, Claude Opus 4.8에 근접했다고 주장합니다. KernelBench는 단순 컴파일 성공 여부가 아니라 PyTorch 기준 구현을 입력으로 받아 에이전트가 생성한 커널의 실제 하드웨어 성능을 평가하는 벤치마크입니다. https:/
RT @elliotarledge: Ich habe einige sehr große Neuigkeiten... KernelBench-Hard mit H100 und B200 (Ergebnisse für einzelne GPUs). UND KernelBench-Mega, getestet auf RTX PRO 6000, H100, B200, ist endlich veröffentlicht! Bei Mega hat jedes Mode
Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/kernelbench