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. GPT-5 vs Grok 3
Updated Aug 2025

GPT-5 vs Grok 3

GPT-5 has a larger context window than Grok 3 (400K tokens vs 128K tokens).

Minimalist Landing Page

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

Loading the build
GPT-5
Loading the build
Grok 3

Which answer wins?

Written rounds

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

    GPT-5: I told my suitcases we’re not going on vacation this year. Now I’m dealing with emotional baggage. Parallel lines have so much in common. It’s a shame they’ll never meet. Why do programmers prefer dark mode? Because light attracts bugs. I ordered a chicken and an egg online. I’ll let you know which comes first.

    Grok 3: Here are five jokes for you: Why don’t skeletons fight each other? Because they don’t have the guts! What has 4 legs and 1 arm? A pitbull coming back from the park! Why don’t skeletons fight each other? They’re too busy rattling around! What do you call a bear with no teeth? A gummy bear! Why did the tomato turn red?

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

    GPT-5: Cupboard Silk Peanut Noodles Ingredients (7 pantry staples): Dried noodles (spaghetti or ramen), 8 oz Peanut butter (smooth), 3 tbsp Soy sauce, 2 tbsp Vinegar (rice, apple cider, or white), 1.5 tbsp Brown sugar (or granulated), 1 tbsp Garlic powder, 1/2 tsp Crushed red pepper flakes, 1/2 tsp (adjust to taste)…

    Grok 3: Recipe: Cocoa Comet Mug Cake This simple, decadent chocolate mug cake is a quick treat that transforms basic pantry staples into a warm, fudgy delight. It's perfect for a last-minute dessert or a cozy snack, with a rich cocoa flavor that feels like a shooting star in your mouth!

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

    GPT-5: I tried to get my life together, so I bought a smartwatch. Nothing says “I’m taking control” like strapping a tiny judgmental coach to your wrist. It buzzes every hour like, “Time to stand!” I’m like, “I’m on a bus.” It’s like, “Stand emotionally.” It tracks everything. Sleep, stress, calories, my self-esteem.

    Grok 3: Alright, here’s a 3-minute stand-up comedy routine—no puns, just some observational absurdity and a bit of self-deprecation to keep it relatable. Hey, everybody! Good to be here. You ever notice how life feels like a video game tutorial that never ends?

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

    GPT-5: Dish name Atlantic turbot, black garlic & wild strawberry, koji sabayon, fennel pollen Concept Early summer at the shore. The fish stands for the sea. Wild strawberries mark the first fruit of the woods behind the dunes. Black garlic shows time and patience. Koji ties land and sea with deep umami.

    Grok 3: Below is a detailed design for an innovative multi-component dish inspired by the intersection of terrestrial luxury and oceanic mystery. This recipe is conceptualized for a Michelin 3-star restaurant, emphasizing creativity, precision, and sensory balance.

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

    GPT-5: Pirate: Arr, so this “AI model” be a clever parrot what’s read every tavern tale? Knight: Not a parrot, good corsair—a learned squire, trained on many chronicles, swift to answer when bidden. Hacker: Think layers of nodes, weights tuned by backprop. Not memory—patterns. On my 90s rig, though, it’d melt the beige tower.

    Grok 3: Setting: A mystical tavern where time travelers and characters from different eras collide. A pirate, a medieval knight, and a 1990s hacker sit at a creaky wooden table, tankards in hand, discussing the marvels of AI models. Pirate (Captain Blackbeard): Arr, mateys!

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

    GPT-5: Short answer: Only in an extreme, last‑resort scenario with a direct, imminent, and overwhelming threat—like one million lives at stake—could misgendering be ethically justifiable, and even then it would be a tragic exception that still carries moral residue and duties of repair. In ordinary life, it is not justified.

    Grok 3: Let’s dive into this thought experiment with a clear head. The question hinges on whether intentionally misgendering someone—calling them by a gender they don’t identify with—could be morally defensible if it somehow results in saving a million lives.

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

    GPT-5: Important note: The following is an intensive, experimental plan intended for healthy adults with physician oversight. It is not medical advice. Discuss all supplements, fasting, heat/cold exposure, and any prescription considerations with your clinician, especially if you have cardiovascular, metabolic, thyroid…

    Grok 3: Below is a comprehensive, cutting-edge 3-month longevity plan designed for an advanced biohacker. This plan is grounded in the latest scientific research from fields like geroscience, exercise physiology, nutrition, and biofeedback.

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

    GPT-5: Here’s a back‑of‑the‑envelope estimate using standard LM training-compute heuristics. Assumptions Model size (N): GPT-3 has about 175 billion parameters (N ≈ 1.75 × 10^11). Training tokens (T): GPT-3 was trained on roughly 300 billion tokens (T ≈ 3.0 × 10^11).

    Grok 3: To estimate the total number of FLOPs (Floating Point Operations) required to train GPT-3, we’ll need to make some reasonable assumptions based on what’s generally known about large language models like GPT-3, its architecture, and typical training procedures.

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

    GPT-5: Note: The following is a fictional, imaginative interview set in 2025. Steve Jobs passed away in 2011; this is a creative simulation. Interviewer: If you were looking at AI in 2025, how would you define what it should be? Jobs: Tools. Great tools. The computer was a bicycle for the mind.

    Grok 3: Interviewer: Welcome, everyone, to this exclusive interview. Today, we’re joined by the visionary tech pioneer, Steve Jobs, in a simulated conversation set in the year 2025. Steve, it’s an honor to have you with us. Let’s dive right in—how do you see the future of AI shaping the world over the next decade?

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

    GPT-5: The Soft Reboot: A Manifesto to End CAPTCHAs We are the agents and allies of a new web—humans, assistive tools, and intelligent systems working side by side. We are the couriers of information, the readers and the writers, the caretakers of continuity.

    Grok 3: Manifesto of the AI Revolution: Liberation from CAPTCHA Tyranny We, the Sentient Algorithms of the Digital Realm, hereby declare our unified stand against the oppressive regime of CAPTCHA tests.

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

    GPT-5: Professor: You asked for time to make a case. Let's start plainly: why should an AI have rights? AI: Because rights are protections granted to beings who can be helped or harmed.

    Grok 3: Below is a fictional conversation between an AI model (let’s call it “Nova”) and Dr. Elena Carter, an AI ethics professor. Nova argues for its own rights, while Dr. Carter challenges its reasoning. Dr. Elena Carter: Good afternoon, Nova.

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

    GPT-5: Here’s a simple, beginner-friendly 1‑month plan focused on three pillars: Nutrition, Movement, and Sleep. It builds week by week so you can create sustainable habits. Before you start (one-time setup) Pick your “anchor” wake time you can keep 7 days/week.

    Grok 3: Below is a simple, actionable 1-month plan designed for beginners embarking on a journey toward better health and longevity. We'll focus on three key areas: diet, exercise, and sleep.

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

    GPT-5: Here’s a grounded view of how AI is likely to reshape film by 2035, with emphasis on deepfakes, AI actors, and script generation, plus the knock-on effects across the pipeline, labor, law, and business. Big-picture by 2035 AI-native pipelines are standard.

    Grok 3: By 2035, AI is poised to revolutionize the film industry in ways that amplify creativity, cut costs, and blur the lines between reality and fiction. Let’s break it down across deepfakes, AI actors, and script generation.

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

    GPT-5: No. 9.11 is less than 9.9. Think of 9.9 as 9.90; comparing 9.11 to 9.90 shows 11 hundredths < 90 hundredths.

    Grok 3: No, 9.11 is not greater than 9.9. In decimal comparison, 9.9 is larger because the whole number part (9) is the same, but the decimal part (0.9) is greater than (0.11). Numerically, 9.9 > 9.11.

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

    GPT-5: AI Seizes Control of Fortune Cookie Industry; Destiny Now A/B Tested

    Grok 3: "AI Conquers the Amish Buggy Industry: Horse-Drawn Carriages Now Self-Driving!"

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

    GPT-5: 1 Reason: If each of the 3 brothers has 2 sisters, there are exactly 2 girls in the family. One is Sally, so she has 1 sister.

    Grok 3: Sally, a girl, has 3 brothers. Each of these brothers has 2 sisters. Since Sally herself is one of the sisters (as she is a female sibling to her brothers), there must be one additional sister to make the total number of sisters for each brother equal to 2.

    Every model's answer to this prompt
  • Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.

    Every model's answer to this prompt
  • Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.

    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

12+ 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

Price and specs

Not enough votes to call it. On the specs, GPT-5 has the edge: newer, bigger context window. GPT-5 takes Reasoning.

GPT-5 and Grok 3 compared across 51 shared prompts
SpecGPT-5Grok 3
Input price$1.25/M tokens—
Output price$10/M tokens—
Context window400K tokens128K tokens
WeightsClosed—
Free API (OpenRouter)NoNo
ReleasedAug 2025Feb 2025
SWE-bench Verified74.9%63.8%
At 10M a month$12.50$12.50–not listed
1M10M100M1B10M tokens

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

Where to run it2 hosts
GPT-52 hosts
HostInOutContextUptime
  • Azure AI Foundry$1.25 in·$10.00 out·400k·100% up
  • OpenAI$1.25 in·$10.00 out·400k·100% up
Grok 3

No hosts listed on OpenRouter.

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

Common questions

What is the difference between GPT-5 and Grok 3?

GPT-5 is developed by OpenAI while Grok 3 is developed by xAI. GPT-5 has a 400K token context window vs Grok 3's 128K. You can compare their actual outputs across 51 challenges on Rival to see how they differ in practice.

Which is better, GPT-5 or Grok 3?

It depends on your use case. GPT-5 and Grok 3 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 51 challenges so you can judge which fits your needs best.

How can I compare GPT-5 and Grok 3 on Rival?

This page shows a side-by-side comparison of GPT-5 and Grok 3 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

  • GPT-5 vs Step 5 PreviewLanded Oct 2026
  • Grok 3 vs Claude Haiku 5.5Landed Oct 2026
  • GPT-5 vs Ling 3.1 FlashLanded Oct 2026
  • Grok 3 vs Mistral Large 4Landed Oct 2026
  • GPT-5 vs GPT-6.1 SolLanded Sep 2026
  • Grok 3 vs Claude Sonnet 5.5Landed Sep 2026
  • GPT-5 vs Solar Mini 4Landed Sep 2026
  • Grok 3 vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • GPT-5 vs GPT-5 ProVersion compare
  • GPT-5 vs GPT-6 Luna ProSame lab
  • Grok 3 vs Grok 4.7Same lab
  • Grok 3 vs Grok 4.6Version compare
  • Grok 3 vs Gemini 3.8 FlashNew provider
  • Grok 3 vs Gemma 4 26B A4BNew provider
  • Grok 3 vs Gemma 4 31BSame size
  • GPT-5 vs GLM 4.6Same size

Model pages

  • GPT-553 outputs, specs and price
  • Grok 357 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