Oriel — AI & technology worth noticing, every day.

Kimi K3.1 scores 55 on Artificial Analysis, placed on the Pareto line

Web page · https://artificialanalysis.ai/models/kimi-k3-1-pro

First seen by Oriel on .

AI summary

Artificial Analysis presents a Kimi K3.1 Pro model-analysis page covering benchmark performance, task costs, token use, speed, latency, and context window, but the extracted text includes no model-specific results.

  • The Intelligence Index v4.3.2 combines 10 evaluations, including AA-Briefcase v1.1, Terminal-Bench 4.0, Humanity's Last Exam, and AA-Omniscience.
  • The page describes cost per task as a benchmark-weighted estimate based on token prices and evaluation usage, excluding repeats for the total index run cost.
  • Performance metrics include output speed, time to first answer token, and estimated time to produce a 500-token response; reasoning time is included where applicable.
  • The text repeatedly reports no publicly available API and does not show Kimi K3.1 Pro's benchmark scores, pricing, context window, or latency values.

#llm benchmarks #model evaluation #inference pricing #llm performance

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hacker News: 110, latest observation ; +86 over observed period since

Comments

Comment count reported by the source.

  • Hacker News: 25, latest observation ; +25 over observed period since

Aliases

SourceExternal IDURL
Hacker News50213337https://artificialanalysis.ai/models/kimi-k3-1-pro Read discussion