GPT-5.4 (Non-reasoning) vs Kimi K3 (Low)

GPT-5.4 (Non-reasoning) vs Kimi K3 (Low). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

OpenAIGPT-5.4 (Non-reasoning)Not ranked · benchmark data missing
Intelligence
18.20
Total cost
-
KimiKimi K3 (Low)Off the frontier
Intelligence
30.10
Total cost
$1190
Verdict

Comparison incomplete

A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

MetricGPT-5.4 (Non-reasoning)Kimi K3 (Low)Difference
Intelligence (higher is better)18.230.1+65.4% Kimi K3 (Low) is 65.4% more intelligent
Total AA cost (lower is better)Not reported$1,190.42— not comparable
End-to-end time (lower is better)7.59s56.42s+643.3% Kimi K3 (Low) is 643.3% slower
Price per 1M tokens (in / out)$2.50 / $15.0$3.00 / $15.0
Input modalitiesText, ImageText, Image
Open this matchup in the interactive pickerGPT-5.4 (Non-reasoning): what beats itKimi K3 (Low): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-5-4-non-reasoning/kimi-k3-low · Markdown: /api/v1/compare/gpt-5-4-non-reasoning/kimi-k3-low?format=md · llms.txt · agent skill