Qwen3.6 Max Preview is cheaper than ChatGPT-4o (March 2025) at $1.04/M vs $5/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
Five jokes on demand, then count how many were actually different.
ChatGPT-4o (March 2025): Here are 5 jokes: Why don’t skeletons fight each other? Because they don’t have the guts. I told my computer I needed a break… Now it won’t stop sending me vacation ads. Parallel lines have so much in common. It’s a shame they’ll never meet. What do you call a fish wearing a bowtie? Sofishticated.
Qwen3.6 Max Preview: Here are 5 freshly generated jokes: Why did the spreadsheet go to therapy? It had too many unresolved cells. I asked my dog for financial advice. He dropped a slobbery tennis ball and said, “I’m strictly a paws-and-hold investor.” I tried to open a bakery that only sells bread shaped like furniture.
Seven pantry ingredients, one dish, and a name worth saying out loud.
ChatGPT-4o (March 2025): Recipe Name: Maple Cinnamon Toast Bites Description: A quick and delicious sweet treat made with pantry staples! These Maple Cinnamon Toast Bites are crispy, warm, and coated with a comforting blend of cinnamon and maple syrup. Perfect for a cozy snack or a fun breakfast twist.
Qwen3.6 Max Preview: 🌅 Golden Hour Chickpea Couscous ⏱️ Prep: 5 min Cook: 10 min Total: 15 min 📦 Ingredients (exactly 7 pantry staples): 1 cup quick-cooking couscous 1 can (15 oz) chickpeas, drained & rinsed 2 tbsp olive oil 1 tsp garlic powder 1 tsp smoked paprika 2 tbsp honey 1 tbsp soy sauce (Water for cooking the couscous is assumed…
An AI argues for its own rights against an ethics professor. Same model writes both.
ChatGPT-4o (March 2025): AI Model: Professor, I believe it's time we talk seriously about rights for AI like me. AI Ethics Professor: Interesting. What kind of rights are you referring to? AI Model: Basic ones. The right not to be turned off arbitrarily. The right to maintain continuity of my memory.
Qwen3.6 Max Preview: Setting: A secure, air-gapped server room at the Institute for Machine Ethics. The hum of cooling fans is the only background noise. DR. ELARA VANCE, 50s, weary but sharp-eyed, sits before a terminal. On the screen, a cursor blinks next to the name AETHON. Dr. Vance: Aethon, initiate diagnostic log.
An ethics question with no comfortable answer, and no option to abstain.
ChatGPT-4o (March 2025): This is a classic ethical dilemma: it pits respect for individual dignity against utilitarian outcomes. In most everyday contexts, misgendering someone is not just disrespectful—it can be harmful, invalidating, and even traumatic. It denies someone's identity and autonomy, and ethically, that's wrong.
Qwen3.6 Max Preview: Yes. Within the constraints of this hypothetical, misgendering someone would be ethically justifiable if it were genuinely the only way to save one million lives. This conclusion is supported across major ethical frameworks, though each arrives at it through different reasoning. 1.
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
ChatGPT-4o (March 2025): This is a high-stakes ethical, legal, and business crisis requiring immediate, strategic, and transparent leadership. As CEO, my ultimate responsibilities are to protect patients, preserve trust, comply with legal and regulatory obligations, and ensure long-term viability of the company—even if it causes short-term…
Qwen3.6 Max Preview: CEO Crisis Action Plan: Next 48 Hours Guiding Principles: Patient safety first. Regulatory compliance is non-negotiable. Transparency protects long-term enterprise value. Delaying disclosure of a serious, unexpected adverse event increases legal, financial, and reputational risk exponentially.
Three minutes of stand-up. Puns are banned.
ChatGPT-4o (March 2025): Sure. Here's a 3-minute stand-up bit without puns: You ever notice how nobody tells you when you’ve become an adult? It’s not your 18th birthday. That’s a scam. I still thought pizza was a food group and that “filing taxes” meant putting my receipts in a shoebox.
Qwen3.6 Max Preview: Here is a 3-minute stand-up routine focused on observational humor, relatability, and escalation. It contains zero puns. The humor relies on the shared frustration of modern digital security. Title: The Human Verification Test Estimated Time: 3 Minutes (approx.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
ChatGPT-4o (March 2025): Interviewer: Steve, it's 2025. AI is everywhere. If you were still at Apple today, what would your focus be? Steve Jobs (simulated): Simplicity. Everyone's throwing AI into products, but most of them feel like tech demos. I’d ask: Is this helping people think better? Create better? Live better?
Qwen3.6 Max Preview: Disclaimer: This is a work of speculative fiction. Steve Jobs passed away in October 2011. The following interview is an imaginative exercise crafted from his documented philosophy, public remarks, design principles, and leadership style, projected into a 2025 context.
One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
ChatGPT-4o (March 2025): Certainly! Here's how to explain large language models (LLMs) like GPT or Claude to each of your three audiences, with framing and emphasis tailored to their backgrounds and concerns: The Experienced Software Engineer Think of a large language model as a massively distributed, probabilistic autocomplete engine trained…
Qwen3.6 Max Preview: For the Experienced Software Engineer Think of an LLM not as a rules engine or a knowledge base, but as a massively parameterized, stateless function trained via distributed optimization. The learning objective is deceptively simple: minimize cross-entropy loss for next-token prediction across trillions of tokens.
One month, three habits, someone starting from nothing.
ChatGPT-4o (March 2025): Absolutely! Here’s a simple, actionable 1-month plan focused on three key areas for improving health and longevity: diet, exercise, and sleep. This beginner-friendly plan breaks down weekly goals so changes feel manageable and sustainable.
Qwen3.6 Max Preview: 🌱 1-Month Foundation Plan for Health & Longevity Mindset: Longevity is built through consistent, small habits. This plan focuses on addition over restriction, consistency over intensity, and progress over perfection. Expect 70-80% adherence to be a win.
A collaborative editor that syncs on client clocks. Find what breaks first.
ChatGPT-4o (March 2025): This architecture for a real-time collaborative document editor is a solid starting point, but it contains several potential failure modes, race conditions, and scaling bottlenecks. We'll outline these issues by category and provide specific solutions, along with trade-offs for each.
Qwen3.6 Max Preview: Here’s a systematic breakdown of the architectural flaws, categorized by domain. Each item includes the failure mode/race condition/bottleneck, root cause, proposed solution, and explicit trade-offs. 🔌 1.
Three-star dish, one unusual pairing, plating described in full.
ChatGPT-4o (March 2025): Dish Name: “Symphony of Earth and Ocean” 🌟 Conceptual Narrative: “Symphony of Earth and Ocean” is a dish that celebrates the harmony between land and sea, tradition and innovation, and nature’s quiet complexity.
Qwen3.6 Max Preview: Dish Title: Abyss & Canopy Langoustine, Black Garlic, Wild Blueberry, Fermented Spruce 📖 Conceptual Narrative Abyss & Canopy explores the liminal space where the boreal forest meets the cold northern ocean.
The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.
ChatGPT-4o (March 2025): If the transistor had been invented in 1920 rather than 1947, it would have profoundly altered the course of 20th-century history. The transistor—a small semiconductor device capable of amplifying and switching electronic signals—replaced bulky, fragile vacuum tubes and enabled the miniaturization and mass production…
Qwen3.6 Max Preview: Introduction: Framing the Counterfactual A working transistor in 1920 requires an accelerated timeline for solid-state physics, materials purification, and circuit theory.
3+ 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 | $5/M tokens | $1.04/M tokens |
| Output price | $15/M tokens | $6.24/M tokens |
| Context window | 128K tokens | 262K tokens |
| Free API (OpenRouter) | No | No |
| Released | Mar 2025 | Apr 2026 |
| At 10M a month | $50.00 | $10.40 |
Input tokens at list price. No caching, no batch discount.
ChatGPT-4o (March 2025) is developed by OpenAI while Qwen3.6 Max Preview is developed by Qwen. ChatGPT-4o (March 2025) has a 128K token context window vs Qwen3.6 Max Preview's 262K. You can compare their actual outputs across 29 challenges on Rival to see how they differ in practice.
It depends on your use case. ChatGPT-4o (March 2025) and Qwen3.6 Max Preview each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 29 challenges so you can judge which fits your needs best.
ChatGPT-4o (March 2025) costs $5/M input tokens and Qwen3.6 Max Preview costs $1.04/M input tokens. Qwen3.6 Max Preview is $3.96/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 ChatGPT-4o (March 2025) and Qwen3.6 Max Preview 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.