Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

February 6, 2026

AI Summary

5 min read

Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

The Startup Ideas Podcast — Greg Isenberg with Morgan Linton

The day Anthropic dropped Opus 4.6, Sam Altman tweeted about GPT-5.3 Codex eighteen minutes later. Morgan Linton, former Sonos executive and now CTO of Boldmetrics, joined Greg Isenberg to put both models head to head in a live build: recreate Polymarket, the multi-billion dollar prediction market app, and see which model performed better. But the real takeaway was not about which model won. It was about how differently they think, and what that means for how you should use them.

The Philosophical Split

Four hours after the models dropped, a Hacker News comment captured the difference perfectly. Linton read it aloud: "With Codex 5.3, the framing is an interactive collaborator. You steer it mid-execution, stay in the loop, course correct as it works. With Opus 4.6, the emphasis is the opposite — a more autonomous, agentic, thoughtful system that plans deeply, runs longer, and asks less of the human."

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of The Startup Ideas Podcast

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **Episode Intro & Guest** - Greg introduces the episode as a head-to-head comparison of Claude Opus 4.6 and GPT-5.3 Codex, with guest Morgan Linton (former Sonos exec, AI investor/builder).
2 (01:30) **Setting Up Opus 4.6 Correctly** - Morgan explains the critical configuration steps to avoid common pitfalls.
3 (08:23) **Philosophical Divergence: Collaborator vs. Autonomous Agent** - A Hacker News post perfectly frames the core difference between the two models.
4 (11:27) **Core Technical Differences** - Morgan breaks down the key specs and use-case tradeoffs.
5 (15:30) **Live Build: Polymarket Competitor - Opus 4.6** - Morgan launches the Opus build with a prompt to create an agent team.
6 (17:00) **Live Build: Polymarket Competitor - Codex 5.3** - Morgan launches the Codex build with a similar but adapted prompt.
7 (22:14) **Codex 5.3 Result: Functional MVP** - Greg tests the Codex-built "Signal Market" app.

+ Full timestamped outline available in the app

Show Notes

I sit down with Morgan Linton, Cofounder/CTO of Bold Metrics, to break down the same-day release of Claude Opus 4.6 and GPT-5.3 Codex. We walk through exactly how to set up Opus 4.6 in Claude Code, explore the philosophical split between autonomous agent teams and interactive pair-programming, and then put both models to the test by having each one build a Polymarket competitor from scratch, live and unscripted. By the end, you'll know how to configure each model, when to reach for one over the other, and what happened when we let them race head-to-head.

Timestamps

00:00 – Intro

03:26 – Setting Up Opus 4.6 in Claude Code

05:16 – Enabling Agent Teams

08:32 – The Philosophical Divergence between Codex and Opus

11:11 – Core Feature Comparison (Context Window, Benchmarks, Agentic Behavior)

15:27 – Live Demo Setup: Polymarket Build Prompt Design

18:26 – Race Begins

21:02 – Best Model for Vibe Coders

22:12 – Codex Finishes in Under 4 Minutes

26:38 – Opus Agents Still Running, Token Usage Climbing

31:41 – Testing and Reviewing the Codex Build

40:25 – Opus Build Completes, First Look at Results

42:47 – Opus Final Build Reveal

44:22 – Side-by-Side Comparison: Opus Takes This Round

45:40 – Final Takeaways and Recommendations

Key Points

Opus 4.6 and GPT-5.3 Codex dropped within 18 minutes of each other and represent two fundamentally different engineering philosophies — autonomous agents vs. interactive collaboration.
To use Opus 4.6 properly, you must update Claude Code to version 2.1.32+, set the model in settings.json, and explicitly enable the experimental Agent Teams feature.
Opus 4.6's standout feature is multi-agent orchestration: you can spin up parallel agents for research, architecture, UX, and testing — all working simultaneously.
GPT-5.3 Codex's standout feature is mid-task steering: you can interrupt, redirect, and course-correct the model while it's actively building.
In the live head-to-head, Codex finished a Polymarket competitor in under 4 minutes; Opus took significantly longer but produced a more polished UI, richer feature set, and 96 tests vs. Codex's 10.
Agent teams multiply token usage substantially — a single Opus build can consume 150,000–250,000 tokens across all agents.

The #1 tool to find startup ideas/