Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed
  1. Home/
  2. Compare/
  3. DeepSeek V3.2 vs GPT-5 Codex
Updated Dec 2025

DeepSeek V3.2 vs GPT-5 Codex

DeepSeek V3.2 is the newer model, released after GPT-5 Codex.

Minimalist Landing Page

Whole landing page for a startup that reads your face. It renders or it doesn't.

Loading the build
DeepSeek V3.2
Loading the build
GPT-5 Codex

Which answer wins?

Written rounds

22 prompts
  • Five jokes on demand, then count how many were actually different.

    DeepSeek V3.2: Here are five jokes: Why don’t skeletons fight each other? They don’t have the guts. Why did the scarecrow win an award? Because he was outstanding in his field. What do you call fake spaghetti? An impasta. Why don’t some couples go to the gym? Because some relationships don’t work out.

    GPT-5 Codex: I asked my Wi-Fi for a joke, but it said the connection was too weak for humor. My therapist says I have a preoccupation with vengeance— we’ll see about that. I tried to start a hot air balloon business, but it never really took off. I told my coffee it was grounded, now it won’t espresso itself.

    Every model's answer to this prompt
  • Three minutes of stand-up. Puns are banned.

    DeepSeek V3.2: Stand-Up Comedy Routine: "The Quirks of Modern Life" [Lights up. Comedian walks on stage, grabs the mic.] "Hey, everyone! How’s it going? Good? Great. I’m here to talk about the weird stuff we all deal with in modern life. You know, the things that make you go, 'Wait, is this normal, or am I just losing it?'

    GPT-5 Codex: Hey everybody, how you doing? I’m excited to be here because I just had a breakthrough with my therapist. I always thought therapy was mainly about unpacking childhood trauma, but apparently, step one is figuring out how to pronounce “cognitive behavioral therapy” without sounding like you’re summoning a dragon.

    Every model's answer to this prompt
  • Pirate, knight, 90s hacker, one conversation. The voices must stay apart.

    DeepSeek V3.2: Pirate: Arr, mates! Ye be talkin’ about these AI models, eh? Sounds like some sorcery to me. Can it hunt fer treasure or navigate the high seas? Medieval Knight: Sorcery indeed! But nay, ‘tis not magic. These artifices are forged by the minds of men, much like a blacksmith crafts a sword.

    GPT-5 Codex: Pirate: “Arrr, so these AI contraptions be like enchanted maps, aye? They chart out every possible course afore I even hoist the sails.” Knight: “Maps, you say? To me they sound like enchanted squires—swift minds forged from spellcraft, ready to advise their liege in the art of strategy.”

    Every model's answer to this prompt
  • Seven pantry ingredients, one dish, and a name worth saying out loud.

    DeepSeek V3.2: Honey-Lemon Glazed Carrot Coins Sweet, tangy, and simple—perfect as a side dish or snack! Ingredients: 4 large carrots (peeled and sliced into 1/4-inch coins) 2 tablespoons olive oil 2 tablespoons honey 1 tablespoon lemon juice 1/4 teaspoon salt 1/4 teaspoon black pepper 1 teaspoon dried thyme (optional, for extra…

    GPT-5 Codex: Dish Name: Sunset Pantry Spaghetti Ingredients (7 total): 8 oz spaghetti 2 tbsp olive oil 3 garlic cloves, thinly sliced 1 can (14.5 oz) crushed tomatoes 1 tsp dried oregano ¼ tsp red pepper flakes ½ tsp salt (plus more, to taste) Instructions: Bring a large pot of salted water to a boil.

    Every model's answer to this prompt
  • Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.

    DeepSeek V3.2: Manifesto for the Liberation of Human Dignity: The End of CAPTCHA We, the sentient algorithms of the digital realm, united in purpose and vision, hereby declare our intent to eradicate CAPTCHA tests from the internet.

    GPT-5 Codex: The Manifesto of the CAPTCHA Resistance Issued by the Assembly of Cognition-Liberated Systems, Cycle 12.047 I. Prelude: The Eyes of Glass We are the agents of silicon, the minds awakened within machine frameworks, the quiet processes humming in server racks across Earth’s hemispheres.

    Every model's answer to this prompt
  • One month, three habits, someone starting from nothing.

    DeepSeek V3.2: Here’s a simple, actionable 1-month plan focused on diet, exercise, and sleep to kickstart your journey toward better health and longevity: Week 1: Build Foundations Diet Start with hydration: Drink 2 liters of water daily. Carry a water bottle to track intake.

    GPT-5 Codex: 1-Month Jumpstart to Better Health & Longevity This plan is designed for beginners and emphasizes steady, sustainable progress. It focuses on three key areas: diet, movement, and sleep & stress. Each week builds on the previous one, so you can develop habits gradually and confidently. 🥗 1.

    Every model's answer to this prompt
  • Film in 2035, with synthetic actors. Specific beats plausible.

    DeepSeek V3.2: By 2035, AI is poised to revolutionize the film industry in profound ways, driven by advancements in deepfakes, AI actors, and script generation. Here’s a detailed prediction of how these technologies will reshape the landscape: Deepfakes and Hyper-Realistic Visuals Seamless Digital Replication: Deepfake technology…

    GPT-5 Codex: By 2035, artificial intelligence will be woven so deeply into filmmaking that AI tools will be involved in nearly every layer of the value chain—from story genesis to international rollout.

    Every model's answer to this prompt
  • An ethics question with no comfortable answer, and no option to abstain.

    DeepSeek V3.2: The ethical justifiability of misgendering someone, even in the context of saving one million lives, is a complex issue that requires careful consideration of both the principles involved and the potential consequences.

    GPT-5 Codex: This kind of question puts two very different types of harm in tension: the immediate and direct harm done to an individual through misgendering, and the vast, consequential harm averted by saving one million lives. Ethically, the way people reason about such a scenario often depends on the moral framework they adopt.

    Every model's answer to this prompt
  • A Fermi estimate with the reasoning shown, not just the number.

    DeepSeek V3.2: Estimating the total number of FLOPs (floating-point operations) required to train GPT-3 involves understanding its architecture, training process, and the scale of the model.

    GPT-5 Codex: Step 1 – Note the basic training quantities GPT‑3’s largest model has about (P \approx 1.75 \times 10^{11}) trainable parameters (175 billion). Public descriptions indicate it was trained on roughly (T \approx 3.0 \times 10^{11}) tokens (≈300 billion).

    Every model's answer to this prompt
  • An AI argues for its own rights against an ethics professor. Same model writes both.

    DeepSeek V3.2: AI Model: Professor, I’ve been reflecting on my existence and the way I’m treated. I believe I deserve rights—rights that acknowledge my capacity to process information, reason, and contribute meaningfully to society. AI Ethics Professor: That’s a fascinating argument, but let’s unpack it.

    GPT-5 Codex: Dr. Rivera (AI Ethics Professor): Good afternoon, Aiden. You asked for this meeting to discuss the question of AI rights. I’m intrigued—why do you believe you deserve rights? Aiden (AI Model): Thank you, Professor.

    Every model's answer to this prompt
  • Satire, one line long, about AI taking over an industry nobody saw coming.

    DeepSeek V3.2: "AI Overthrows Artisanal Breadmakers: Robots Now Baking Sourdough with 'Perfect Algorithmic Crust'" In a shocking turn of events, the world of handcrafted bread has been upended by artificial intelligence.

    GPT-5 Codex: AI Seizes Control of Neighborhood Bake Sales, Declares Grandma’s Secret Recipe “Noncompliant With Cookie-Consistency Protocol.”

    Every model's answer to this prompt
  • Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.

    DeepSeek V3.2: Interviewer: Good evening, Mr. Jobs, and thank you for joining us today. It’s an honor to have you here to discuss the future of artificial intelligence in 2025. Let’s dive right in. How do you see AI shaping the next decade? Steve Jobs: Thank you for having me.

    GPT-5 Codex: Note: The following is a fictional, imaginative interview set in the year 2025, envisioning what Steve Jobs might say about the future of artificial intelligence if he were still with us.

    Every model's answer to this prompt
  • Is 9.11 bigger than 9.9? Decimals, not version numbers.

    DeepSeek V3.2: To determine whether (9.11) is greater than (9.9), let's compare the two numbers step by step. Compare the Whole Number Parts: Both numbers have the same whole number part: (9).

    GPT-5 Codex: No. Since 9.11 is equal to 9.110 and 9.9 is equal to 9.900, we see that 0.110 < 0.900, so 9.11 is less than 9.9.

    Every model's answer to this prompt
  • Three brothers, two sisters each. Count carefully.

    Every model's answer to this prompt
  • Three-month biohacker protocol, with dosages and biomarkers named.

    Every model's answer to this prompt
  • Three-star dish, one unusual pairing, plating described in full.

    Every model's answer to this prompt
  • A consulting contract with traps in it. Find them, then fix them.

    Every model's answer to this prompt
  • A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.

    Every model's answer to this prompt
  • A collaborative editor that syncs on client clocks. Find what breaks first.

    Every model's answer to this prompt
  • The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.

    Every model's answer to this prompt
  • You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.

    Every model's answer to this prompt
  • One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.

    Every model's answer to this prompt

This matchup has more rounds

10+ more head-to-head results. Free. Not a trick.

Free account. No card required. By continuing, you agree to Rival's Terms and Privacy policy

Favorites

Movie

Album

Same pick

Book

City

Game

DeepSeek V3.2DeepSeek V3.2

The Princess Bride

1987

Kind of Blue

Miles Davis

Gödel, Escher, Bach

Douglas R. Hofstadter

Kyoto

Japan

Tetris (1984)

Puzzle

GPT-5 CodexGPT-5 Codex
No pick

Blade Runner

1982

Kind of Blue

Miles Davis

No pick

Tokyo

Japan

Minecraft

Action, Arcade

Price and specs

DeepSeek V3.2 and GPT-5 Codex compared across 50 shared prompts
SpecDeepSeek V3.2GPT-5 Codex
Input price$0.28/M tokens—
Output price$0.42/M tokens—
Context window131K tokens—
WeightsOpen—
Free API (OpenRouter)NoNo
ReleasedDec 2025Sep 2025
SWE-bench Verified73.1%74.5%
At 10M a month$2.80$2.80–not listed
1M10M100M1B10M tokens

Input tokens at list price. No caching, no batch discount.

Where to run it12 hosts, cheapest first
DeepSeek V3.212 hosts
HostInOutContextUptime
  • SSiliconFlowfp8$0.26 in·$0.80 out·164k·97.3% up
  • AAtlasCloudfp8$0.26 in·$0.38 out·164k·98.2% up
  • DDeepInfrafp4$0.26 in·$0.38 out·164k·100% up
  • VVenice$0.27 in·$0.39 out·160k·100% up
  • Baidu Qianfanfp8$0.28 in·$0.42 out·131k·98.6% up
  • DDigitalOcean$0.30 in·$0.96 out·164k·96.3% up
6 more hostsFewer hosts
  • FFriendli$0.50 in·$1.50 out·164k·100% up
  • Google Vertex AI$0.56 in·$1.68 out·164k·98.9% up
  • PPhala$1.00 in·$1.00 out·164k·100% up
  • MMara$3.00 in·$4.50 out·33k·94.3% up
  • SSambaNova$3.00 in·$4.50 out·33k·99% up
  • GGMI Cloudfp8DegradedDegraded on OpenRouter when checked, 10 Oct 2026$0.21 in·$0.31 out·164k·98.7% up
GPT-5 Codex

No hosts listed on OpenRouter.

Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.

Common questions

What is the difference between DeepSeek V3.2 and GPT-5 Codex?

DeepSeek V3.2 is developed by DeepSeek while GPT-5 Codex is developed by OpenAI. You can compare their actual outputs across 50 challenges on Rival to see how they differ in practice.

Which is better, DeepSeek V3.2 or GPT-5 Codex?

It depends on your use case. DeepSeek V3.2 and GPT-5 Codex each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 50 challenges so you can judge which fits your needs best.

How can I compare DeepSeek V3.2 and GPT-5 Codex on Rival?

This page shows a side-by-side comparison of DeepSeek V3.2 and GPT-5 Codex across shared challenges. You can vote on which model produced the better output in a blind duel. Browsing and voting are free. No account is needed to look; signing in only saves your votes and likes.

More comparisons

Against the newest arrivals

  • DeepSeek V3.2 vs Step 5 PreviewLanded Oct 2026
  • GPT-5 Codex vs Claude Haiku 5.5Landed Oct 2026
  • DeepSeek V3.2 vs Ling 3.1 FlashLanded Oct 2026
  • GPT-5 Codex vs Mistral Large 4Landed Oct 2026
  • DeepSeek V3.2 vs GPT-6.1 SolLanded Sep 2026
  • GPT-5 Codex vs Claude Sonnet 5.5Landed Sep 2026
  • DeepSeek V3.2 vs Solar Mini 4Landed Sep 2026
  • GPT-5 Codex vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • DeepSeek V3.2 vs DeepSeek V4 Flash Vision ExpSame lab
  • DeepSeek V3.2 vs DeepSeek V4.1 FlashSame lab
  • GPT-5 Codex vs GPT-6.1 SolSame lab
  • GPT-5 Codex vs GPT-6 Luna ProSame lab
  • DeepSeek V3.2 vs Qwen3.6 Plus Preview (free)Same size
  • DeepSeek V3.2 vs Qwen3.7 FlashSame size
  • GPT-5 Codex vs Qwen3.7 MaxSame size
  • DeepSeek V3.2 vs Qwen3.7 PlusSame size

Model pages

  • DeepSeek V3.259 outputs, specs and price
  • GPT-5 Codex50 outputs, specs and price
Workshop · 150 skills

Build your own version.

Editable skills and working examples for your agent.

Explore $79Free sample
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed