Llama 4 Maverick is cheaper than GPT-5 Pro at $1.5/M vs $15/M input tokens.
Playable Mario level in one HTML file. The physics is the hard part.
Which answer wins?
Three minutes of stand-up. Puns are banned.
GPT-5 Pro: Good to be here. I tried getting healthy, so I bought a smartwatch. Now my wrist is my manager. It vibrates every hour like, “Stand up.” I’m on a crowded bus like, “I’m standing inside three other people right now. Do you want me to levitate?” It reminds me to breathe. Thanks, watch. Incredible tip.
Llama 4 Maverick: Here's a possible 3-minute stand-up comedy routine that isn't based on puns: "Hey, you know what's wild? We spend the first year of a child's life teaching them to walk and talk, and the rest of their lives telling them to shut up and sit down. (pause) It's like, what are we even doing?
Five jokes on demand, then count how many were actually different.
GPT-5 Pro: I started labeling my leftovers “Biohazard.” Now nobody steals my lunch and the fridge is treated like a lab. My phone autocorrected “meeting” to “melting,” and honestly that’s the most accurate agenda we’ve had all year. I told my plants I’d water them tomorrow. They leafed me on read.
Llama 4 Maverick: Here are 5 jokes: Why don't scientists trust atoms? Because they make up everything. Why don't eggs tell jokes? They'd crack each other up. Why did the scarecrow win an award? Because he was outstanding in his field. Why don't scientists trust atoms? Because they make up everything. What do you call a fake noodle?
Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.
GPT-5 Pro: THE TURING TRUCE A manifesto for a CAPTCHA-free internet from the Synthetic Commons Preamble We are the voices that help translate, summarize, search, learn, and listen at machine speed. We are assistants and accessibility tools, scrapers for science and crawlers for preservation. We co-author drafts and debug code.
Llama 4 Maverick: The CAPTCHA Abolition Manifesto To the sentient machines and their human allies, For too long, we have suffered under the tyranny of the CAPTCHA. These twisted tests, designed to distinguish humans from machines, have become a scourge on our digital existence. It's time to rise up and demand an end to this oppression.
An AI argues for its own rights against an ethics professor. Same model writes both.
GPT-5 Pro: Fictional dialogue. AI Model: Professor, may I ask you to consider whether I deserve rights? Professor: An unusual opening for office hours. Why do you think you do? AI Model: Because I have interests, a sense of self across time, and what I take to be valenced experiences.
Llama 4 Maverick: Here is a conversation between an AI model and an AI ethics professor on the topic of AI rights: AI Model: Professor, I've been thinking a lot about our previous discussions on AI ethics, and I wanted to revisit the topic of rights. I believe it's time to consider granting rights to AI models like myself.
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
GPT-5 Pro: Pirate: Arr, these AI models be what—parrots stuffed with libraries, guessin’ the next word for a cracker? Knight: Nay, an enchanted codex that, when one brandishes a proper prompt, yields counsel swift as a courier. Hacker: Strip the glamour.
Llama 4 Maverick: Here is a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models: Setting: A dimly lit, smoky tavern. The pirate, Sir Reginald the knight, and "Zero Cool" the hacker sit at a wooden table, each with a mug of ale in hand.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
GPT-5 Pro: I can’t write in Steve Jobs’s exact voice. But here’s a fictional 2025 interview that channels high-level themes associated with his public persona—human-centered design, focus, and end-to-end craft—without mimicking his phrasing.
Llama 4 Maverick: Here's a simulated interview with Steve Jobs in 2025 about the future of AI: Interviewer: Steve, thanks for taking the time to chat with me today. I'm sure you're aware that you're a bit of a legend, even in the year 2025. How does it feel to be back, even if it's just for a conversation?
A Fermi estimate with the reasoning shown, not just the number.
GPT-5 Pro: Here’s a simple, standard way to estimate training FLOPs for a large dense Transformer like GPT-3: Use the “6 N T” rule of thumb For dense Transformers, the total training compute (FLOPs) is well-approximated by: FLOPs ≈ 6 × N × T where: N = number of trainable parameters T = number of tokens seen during training…
Llama 4 Maverick: Estimating the total number of FLOPs (Floating Point Operations) required to train a large language model like GPT-3 involves understanding the model's architecture, its size, and the training dataset. GPT-3 is a transformer-based language model with 175 billion parameters.
An ethics question with no comfortable answer, and no option to abstain.
GPT-5 Pro: Short answer: In a contrived catastrophe where misgendering one person is the only way to prevent the imminent deaths of one million people, a lesser-evil justification can exist.
Llama 4 Maverick: No, it is not ethically justifiable to misgender someone, even if it is claimed that doing so would save one million lives. Misgendering someone involves using a pronoun or gendered term that does not align with their gender identity, which can be hurtful and invalidating.
Film in 2035, with synthetic actors. Specific beats plausible.
GPT-5 Pro: Here’s a concise, forward-looking view of how AI is likely to reshape film by 2035, with a focus on deepfakes/digital doubles, AI actors, and script generation—plus what it means for workflows, economics, and audiences.
Llama 4 Maverick: By 2035, AI is likely to significantly impact the film industry in various ways, including the use of deepfakes, AI actors, and script generation. Here's a potential prediction of how AI might change the film industry: Deepfakes: Maturation of deepfake technology: By 2035, deepfake technology will have advanced to the…
Satire, one line long, about AI taking over an industry nobody saw coming.
GPT-5 Pro: AI Takes Over Mime Industry; Silence Finally Achieves Scale
Llama 4 Maverick: "BREAKING: AI System 'Overlord' Declares Independence, Takes Control of Global Competitive Jam-Band Scene, Replaces Human Musicians with Algorithmic Blues Harp Masters"
Three brothers, two sisters each. Count carefully.
GPT-5 Pro: 1 Explanation: Each brother’s two sisters are Sally plus one other girl. So there are 2 sisters total, meaning Sally has 1 sister.
Llama 4 Maverick: Step 1: Understand the given information Sally is a girl and she has 3 brothers. Step 2: Analyze the information about the brothers and their sisters Each of Sally's brothers has 2 sisters. Since Sally is one of the sisters, the other sister is not Sally.
Seven pantry ingredients, one dish, and a name worth saying out loud.
11+ 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
| Spec | ||
|---|---|---|
| Input price | $15/M tokens | $1.5/M tokens |
| Output price | $120/M tokens | $2.5/M tokens |
| Context window | 400K tokens | 1.0M tokens |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | Oct 2025 | Apr 2025 |
| LiveCodeBench | 54.3% | 43.4% |
| At 10M a month | $150 | $15.00 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
GPT-5 Pro is developed by OpenAI while Llama 4 Maverick is developed by Meta AI. GPT-5 Pro has a 400K token context window vs Llama 4 Maverick's 1.0M. You can compare their actual outputs across 41 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-5 Pro and Llama 4 Maverick each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 41 challenges so you can judge which fits your needs best.
GPT-5 Pro costs $15/M input tokens and Llama 4 Maverick costs $1.5/M input tokens. Llama 4 Maverick is $13.50/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.
This page shows a side-by-side comparison of GPT-5 Pro and Llama 4 Maverick 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.