---
title: Test-Time Compute
seo_title: Test-Time Compute — video
description: Test-time compute as a second scaling axis. The three levers—more steps, more candidates and more structure—and their quality, cost and latency tradeoffs in reasoning models.
keywords: test-time compute, LLM reasoning, best-of-N, chain of thought, PRM, ORM, scaling laws, extended reasoning, budget forcing, DeepSeek R1, MCTS, self-consistency, Tree of Thoughts
date: '2026-04-10T00:00:00+00:00'
robots: index,follow,max-snippet:-1,max-image-preview:large,max-video-preview:-1
hide:
- toc
- navigation
video_watch_page: true
---


<div class="s5-video-watch" data-s5-video-watch data-video-id="videos-series-modelos-razonadores-03-test-time-compute-md">
  <header class="s5-video-watch__header">
    <div class="s5-video-watch__crumbs"><a href="https://5sigmas.com/en/videos/">All videos</a><span>Reasoning</span><span>1:00</span></div>
    <h1>Test-Time Compute</h1><p>Test-time compute as a second scaling axis. The three levers—more steps, more candidates and more structure—and their quality, cost and latency tradeoffs in reasoning models.</p>
  </header>
  <div class="s5-video-watch__player">
    <video controls crossorigin="anonymous" preload="metadata" poster="/en/series/modelos-razonadores/03-test-time-compute.jpg" playsinline data-s5-watch-player><source src="/en/series/modelos-razonadores/03-test-time-compute.mp4" type="video/mp4">Your browser does not support the video element.</video>
    <p>Links containing <code>?t=</code> open the video at a specific second.</p>
  </div>
  <section class="s5-video-watch__summary" aria-labelledby="video-summary-title">
    <div class="s5-video-watch__section-head"><span class="s5-eyebrow">Video summary</span><h2 id="video-summary-title">The ideas to retain</h2></div>
    <div class="s5-video-watch__snippet-grid"><article><span>01</span><h2>1. What test-time compute is and why it matters</h2><p>For a long time, the main known lever for improving an LLM was training scale: more parameters, more data and more training compute. The original scaling-law work (Kaplan et al., 2020)…</p></article>
<article><span>02</span><h2>2. The three levers</h2><p>There are three principal mechanisms for translating additional inference compute into better answers.</p></article>
<article><span>03</span><h2>Lever 1: More internal steps</h2><p>Chain-of-thought (Wei et al., 2022) is the most direct mechanism. Instead of producing the final answer immediately, the model first generates a sequence of intermediate steps that…</p></article></div>
  </section>
  
  
  <aside class="s5-video-watch__source"><div><span class="s5-eyebrow">Context and evidence</span><h2>Continue with the full article</h2><p>The chapter develops the mechanism, primary sources, limitations and connections to the rest of the series.</p></div><a class="s5-video-watch__source-link" href="https://5sigmas.com/en/series/modelos-razonadores/03-test-time-compute/">Read the article →</a></aside>
  <section class="s5-video-watch__related" aria-labelledby="related-videos-title"><div class="s5-video-watch__section-head"><span class="s5-eyebrow">Next step</span><h2 id="related-videos-title">Related videos</h2></div><div class="s5-video-watch__related-grid"><article><a href="https://5sigmas.com/en/videos/series/modelos-razonadores/05-riesgos/"><img src="https://5sigmas.com/en/series/modelos-razonadores/05-riesgos.jpg" alt="" loading="lazy" width="1280" height="720"><span>Reasoning · 1:00</span><strong>Reasoning Risks and Production Controls</strong></a></article>
<article><a href="https://5sigmas.com/en/videos/series/modelos-razonadores/04-latencia-streaming/"><img src="https://5sigmas.com/en/series/modelos-razonadores/04-latencia-streaming.jpg" alt="" loading="lazy" width="1280" height="720"><span>Reasoning · 0:59</span><strong>Latency, Streaming and Product Design</strong></a></article>
<article><a href="https://5sigmas.com/en/videos/series/modelos-razonadores/02-fallos/"><img src="https://5sigmas.com/en/series/modelos-razonadores/02-fallos.jpg" alt="" loading="lazy" width="1280" height="720"><span>Reasoning · 0:59</span><strong>How Reasoning Fails</strong></a></article></div></section>
</div>