‹ BackHN Continuity

Thread

Grok 4.7

609 points · 541 comments · meetpateltech

  1. simonw · · focus · HN ↗
    <a href="https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F58dc4e8ec482330856fce89dac670727" rel="nofollow">https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=ht... - default reasoning level.

    Here&#x27;s reasoning level high: <a href="https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F8ab126bda2b384264b3ad931e3ebb8b4" rel="nofollow">https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=ht...

    For some reason reasoning effort low and medium used similar numbers of tokens, and xhigh used less than high. I think I need to try without OpenRouter in the middle.

    UPDATE: I tried again with the xAI API directly: <a href="https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F5a1819a2bd24bb642f38c4bc6733090f" rel="nofollow">https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=ht... - not a great deal of difference between reasoning levels, and this time xhigh and low used the same number of reasoning tokens for some reason.

    For comparison here&#x27;s a fresh run against Grok 4.6: <a href="https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Ffedc404b9aa8e6fca31d59c898dabba0" rel="nofollow">https:&#x2F;&#x2F;tools.simonwillison.net&#x2F;markdown-svg-renderer?url=ht...

    1. nicolamanzini · · focus · HN ↗

      [dead]

      1. danappelxx · · focus · HN ↗
        Wow, thanks for sharing, fun benchmark!
      2. iankp · · focus · HN ↗
        Would be amazing to see this for frontend.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.