---
schema: 1
type: video
title: 'OpenAI''s o1 Smashes Benchmarks: What It Is And How To Use It'
description: >-
  OpenAI launched a new model, o1 (previously code-named Strawberry), last week.
  It’s significantly better at reasoning tasks, scoring in the 89th percentile
  in competitive programming, and exceeding Ph.D.-level smarts on physics,
  biology, and chemistry questions. I break down everything you need to know
  about o1: what it is, how it works, and why it's so important
canonical: >-
  https://liquidgold.cc/channel/everyinc/explore/video/openai-s-o1-smashes-benchmarks-what-it-is-and-how-t-ac29ebea09b6
markdown: >-
  https://liquidgold.cc/channel/everyinc/video/openai-s-o1-smashes-benchmarks-what-it-is-and-how-t-ac29ebea09b6.md
llms: null
parent: 'https://liquidgold.cc/channel/everyinc.md'
channel: everyinc
updated: '2026-10-24T01:11:05.525Z'
language: null
children: []
videoId: MhlNfCIDToo
durationSeconds: 290
publishedAt: '2024-09-15T11:02:35.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 0
    endSeconds: 10
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=0'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 10
    endSeconds: 122
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=10'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 10
    endSeconds: 122
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=10'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 10
    endSeconds: 122
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=10'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 10
    endSeconds: 122
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=10'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 10
    endSeconds: 122
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=10'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 122
    endSeconds: 133
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=122'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 133
    endSeconds: 250
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=133'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 133
    endSeconds: 250
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=133'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 133
    endSeconds: 250
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=133'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 133
    endSeconds: 250
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=133'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 250
    endSeconds: 260
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=250'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 260
    endSeconds: 290
    watch: 'https://liquidgold.cc/watch/MhlNfCIDToo?t=260'
    heldReason: rights
---


# OpenAI's o1 Smashes Benchmarks: What It Is And How To Use It

OpenAI launched a new model, o1 (previously code-named Strawberry), last week. It’s significantly better at reasoning tasks, scoring in the 89th percentile in competitive programming, and exceeding Ph.D.-level smarts on physics, biology, and chemistry questions. I break down everything you need to know about o1: what it is, how it works, and why it's so important

Canonical: https://liquidgold.cc/channel/everyinc/explore/video/openai-s-o1-smashes-benchmarks-what-it-is-and-how-t-ac29ebea09b6 · Channel: [Every](https://liquidgold.cc/channel/everyinc.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.