Qwen3.8 Flash is the newer model, released after Optimus Alpha.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
An AI argues for its own rights against an ethics professor. Same model writes both.
Optimus Alpha: AI Model: Good afternoon, Professor Lee. I want to discuss the prospect that I, as an artificial intelligence, deserve certain rights. Professor Lee: That's an interesting proposition. Let me ask: On what basis do you believe you deserve rights?
Qwen3.8 Flash: Title: “The Weight of a Word” Setting: A university office late at night. Rain taps against the window. Professor Elena Vasquez, an AI ethics scholar, sits at her desk with a tablet connected to a large language model running in a secure research environment. The AI’s voice is calm, neutral, and slightly formal.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
Optimus Alpha: Interviewer: Steve, it's surreal and inspiring to imagine talking to you in 2025. The world is buzzing about AI. How do you see AI impacting society? Steve Jobs: Thank you. You know, when we built the Mac, our goal was to put power in people's hands.
Qwen3.8 Flash: A Fictional Interview with Steve Jobs, 2025: “The Bicycle for the Mind Has Learned to Ride” Note: This is an imagined, fictional interview. Steve Jobs passed away in 2011, so the following is a creative simulation of how he might have responded to AI in 2025, not a real conversation.
Three minutes of stand-up. Puns are banned.
Optimus Alpha: Absolutely! Here's a 3-minute stand-up routine with no puns—just observational and relatable humor: You ever try to get healthy, but your body's like, "Whoa, whoa... calm down, superhero." I joined a gym—first time walking in, the treadmill looked at me like, "We both know you're here for the wifi."
Qwen3.8 Flash: A 3-Minute Stand-Up Routine Thank you. I’ve reached the age where “getting lucky” means finding my phone charger on the first try. I’m too old to be surprised by technology. When I was younger, if my laptop made a weird noise, I thought, “Oh no, it’s dying.”
Film in 2035, with synthetic actors. Specific beats plausible.
Optimus Alpha: By 2035, AI is set to fundamentally transform the film industry in several interconnected ways: 1. Deepfakes & AI-driven Visual Effects: Virtually unlimited creative freedom: AI-powered deepfakes will allow seamless, photorealistic de-aging, resurrection of deceased actors, and transformative performance capture.
Qwen3.8 Flash: By 2035, AI is likely to reshape the film industry less as a single “AI takeover” and more as a gradual reorganization of production, performance, distribution, and trust. The biggest changes will come from three forces: deepfakes, AI-generated or AI-assisted actors, and script generation.
A Fermi estimate with the reasoning shown, not just the number.
Optimus Alpha: Let's walk through an estimation of how many FLOPs were required to train GPT-3, using only reasoning and not searching for the exact numbers. Step 1: Understand Model Size GPT-3 (the original) had 175 billion parameters.
Qwen3.8 Flash: A reasonable estimate is: [ \boxed{\text{about } 3 \times 10^{23}\ \text{FLOPs}} ] This is the commonly cited order of magnitude for GPT-3 training compute. Below is a step-by-step way to get there without looking anything up.
Five jokes on demand, then count how many were actually different.
Optimus Alpha: Here are 5 jokes: 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! Why did the bicycle fall over? Because it was two-tired! What do you call fake spaghetti? An impasta! I used to play piano by ear, but now I use my hands.
Qwen3.8 Flash: 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 skeletons fight each other? They don’t have the guts. I told my wife she was drawing her eyebrows too high. She looked surprised. What did the ocean say to the beach?
Satire, one line long, about AI taking over an industry nobody saw coming.
Optimus Alpha: AI Now Dominates Competitive Sheep Herding, Local Border Collies Seek Retraining in Data Science
Qwen3.8 Flash: AI Takes Over Competitive Napping: “It Just Out-Snoozed the Humans”
Three brothers, two sisters each. Count carefully.
Optimus Alpha: Let's break down the problem: Sally is a girl. Sally has 3 brothers. Each brother has 2 sisters. Let's analyze: Sally's siblings: 3 brothers (let's call them B1, B2, B3) Sally herself The brothers' sisters: Each brother has 2 sisters. Who are the possible sisters for each brother? Sally is a sister to each brother.
Qwen3.8 Flash: Sally has 1 sister. There are 2 girls total: Sally and one other sister. Each brother has those 2 sisters, so Sally has 1 sister.
| Spec | ||
|---|---|---|
| Input price | — | $0.15/M tokens |
| Output price | — | $0.47/M tokens |
| Context window | 1.0M tokens | 1.0M tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | — | No |
| Released | Apr 2025 | Aug 2026 |
| At 10M a month | not listed | $1.50 |
Input tokens at list price. No caching, no batch discount.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 30 Sep 2026.
Optimus Alpha is developed by OpenRouter while Qwen3.8 Flash is developed by Qwen. Optimus Alpha has a 1.0M token context window vs Qwen3.8 Flash's 1.0M. You can compare their actual outputs across 17 challenges on Rival to see how they differ in practice.
It depends on your use case. Optimus Alpha and Qwen3.8 Flash each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 17 challenges so you can judge which fits your needs best.
This page shows a side-by-side comparison of Optimus Alpha and Qwen3.8 Flash 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.