conv.

All stories
AIQuiet 5d · day 5

Artificial Analysis benchmarks Grok 4.7, finds high intelligence but verbose output

Grok 4.7 scores 46 on Artificial Analysis Intelligence Index, well above average, but generates 2.5x more tokens than comparable models.

newest coverage 4d agosummary written 4d ago3 pieces13 likes & upvotes1 comments Hacker NewsMastodonNewswires

What to know

  • Grok 4.7 achieves an intelligence score of 46 on Artificial Analysis's benchmark, nearly double the median of 24, placing it among leading models.
  • The model generates 2.5x more tokens than comparable models during evaluation, indicating significant inefficiency and verbosity in output generation.
  • Grok 4.7 pricing is competitive with peers at $2.00 per 1M input tokens and $6.00 per 1M output tokens, both at or below median rates.

“Pricing for Grok 4.7 (xhigh) is $2.00 per 1M input tokens (moderately priced, median: $2.00) and $6.00 per 1M output tokens (moderately priced, median: $10.00).”

Artificial Analysis, Benchmarking firm · Artificial Analysis ↗

Artificial Analysis AI benchmarking firmGrok (xAI) AI model subject

How it unfolded 2 developments, newest first · click a bar or a number to jump articlesposts

Peak 2 pieces in two hours at Sep 21, 11 AM; 3 pieces over 5 days (1 article · 2 posts) Sep 21, 11 AM — 2 pieces · 1 article · 1 post — Hacker News 1, Newswires 1Sep 21, 1 PM — 1 piece · 1 post — Mastodon 1Sep 21, 3 PM — quietSep 21, 5 PM — quietSep 21, 7 PM — quietSep 21, 9 PM — quietSep 21, 11 PM — quietSep 22, 1 AM — quietSep 22, 3 AM — quietSep 22, 5 AM — quietSep 22, 7 AM — quietSep 22, 9 AM — quietSep 22, 11 AM — quietSep 22, 1 PM — quietSep 22, 3 PM — quietSep 22, 5 PM — quietSep 22, 7 PM — quietSep 22, 9 PM — quietSep 22, 11 PM — quietSep 23, 1 AM — quietSep 23, 3 AM — quietSep 23, 5 AM — quietSep 23, 7 AM — quietSep 23, 9 AM — quietSep 23, 11 AM — quietSep 23, 1 PM — quietSep 23, 3 PM — quietSep 23, 5 PM — quietSep 23, 7 PM — quietSep 23, 9 PM — quietSep 23, 11 PM — quietSep 24, 1 AM — quietSep 24, 3 AM — quietSep 24, 5 AM — quietSep 24, 7 AM — quietSep 24, 9 AM — quietSep 24, 11 AM — quietSep 24, 1 PM — quietSep 24, 3 PM — quietSep 24, 5 PM — quietSep 24, 7 PM — quietSep 24, 9 PM — quietSep 24, 11 PM — quietYesterday, 1 AM — quietYesterday, 3 AM — quietYesterday, 5 AM — quietYesterday, 7 AM — quietYesterday, 9 AM — quietYesterday, 11 AM — quietYesterday, 1 PM — quietYesterday, 3 PM — quietYesterday, 5 PM — quietYesterday, 7 PM — quietYesterday, 9 PM — quietYesterday, 11 PM — quietToday, 1 AM — quietToday, 3 AM — quietToday, 5 AM — quietToday, 7 AM — quietToday, 9 AM — quiet 1–2
Sep 22Sep 23Sep 24yesterdaynow · 11:45 AM ET
  1. 2

    Hacker News shares Grok 4.7 analysis with community

    The Artificial Analysis benchmark was shared on Hacker News, surfacing the detailed evaluation to the developer community. The submission was titled 'Grok 4.7 Intelligence, Performance and Price Analysis' and gained 11 points.

  2. 1

    Artificial Analysis publishes Grok 4.7 benchmark evaluation

    Artificial Analysis released a comprehensive intelligence, performance, and price analysis of Grok 4.7 (xhigh). The model scored 46 on their Intelligence Index, placing it well above average. The analysis found the model notably slow and very verbose, generating 240M tokens during evaluation versus a median of 94M.

    “Grok 4.7 (xhigh) is amongst the leading models in intelligence and reasonably priced when comparing to other models of similar price. It's also notably slow and very verbose.”
    — Artificial Analysis
    1. 1 outlet Grok 4.7 (xhigh) Intelligence, Performance & Price Analysis

      first by Artificial Analysis, 4d ago