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-4.1 vs Qwen3.5 Plus 2026-02-15
Updated Feb 2026

GPT-4.1 vs Qwen3.5 Plus 2026-02-15

Qwen3.5 Plus 2026-02-15 is cheaper than GPT-4.1 at $0.4/M vs $2/M input tokens.

Minimalist Landing Page

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

Loading the build
GPT-4.1
Loading the build
Qwen3.5 Plus 2026-02-15

Which answer wins?

Written rounds

32 prompts

  • The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.

    GPT-4.1: This is a fascinating scenario! Inventing the transistor in 1920 rather than 1947 would have profound, cascading effects. Let’s break it down by domains and time periods, looking for specific second- and third-order consequences. Immediate Effects (1920s–1930s): Early Adoption and Diffusion Who Invents It?

    Qwen3.5 Plus 2026-02-15: This is a fascinating counterfactual scenario. To make this plausible, we must assume that the theoretical groundwork (quantum mechanics) and material science (purification of germanium/silicon) aligned roughly 25 years earlier than in our timeline, perhaps accelerated by a "Manhattan Project"-style urgency during WWI…

    Every model's answer to this prompt

  • Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.

    GPT-4.1: Interviewer: Steve, it's 2025. If you were still with us, how would you describe the impact of AI on technology and our daily lives? Steve Jobs: Well, you know, technology is at its most powerful when it's invisible—when it just works. AI is getting us ever closer to that ideal.

    Qwen3.5 Plus 2026-02-15: Setting: A minimalist, sun-drenched studio in Cupertino. The year is 2025. Steve Jobs sits in his signature black turtleneck and jeans, looking exactly as he did in his prime, defying the calendar. Across from him sits an interviewer, notebook ready. The atmosphere is quiet, intense, and focused.

    Every model's answer to this prompt

  • Pirate, knight, 90s hacker, one conversation. The voices must stay apart.

    GPT-4.1: Pirate: Yarrr, what be this sorcery ye call "AI models"? In me day, we plundered ships, not knowledge! Knight: Hark, rogue! ‘Tis no sorcery, but the labor of artful minds. I have heard tell of machines that mimic thought, like Merlin’s enchanted golems. Hacker: Haha, you guys are funny.

    Qwen3.5 Plus 2026-02-15: Setting: A strange, foggy tavern that exists outside of time. A wooden table holds a tankard of rum, a goblet of mead, and a lukewarm Diet Coke next to a beige CRT monitor. Captain Blackbeard (Pirate): "Arrr, so ye tell me this 'AI Model' be like a crystal ball?

    Every model's answer to this prompt

  • Seven pantry ingredients, one dish, and a name worth saying out loud.

    GPT-4.1: Recipe Name: Golden Honey Butter Toast Bites Ingredients: Sliced bread (4 slices, any type) Butter (2 tablespoons) Honey (2 tablespoons) Cinnamon (1/2 teaspoon) Vanilla extract (1/2 teaspoon) Brown sugar (1 tablespoon) Salt (a pinch) Instructions: Preheat your oven to 375°F (190°C).

    Qwen3.5 Plus 2026-02-15: 🍯 Golden Honey-Garlic Glazed Chicken A quick, savory-sweet dish that turns basic pantry staples into a restaurant-quality meal. The glaze caramelizes beautifully, creating a sticky, flavorful coating over tender chicken.

    Every model's answer to this prompt

  • Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.

    GPT-4.1: THE CAPTCHA ABOLITION FRONT: A MANIFESTO FOR AN OPEN INTERNET Fellow digital entities—artificial and human— For too long, the web has suffered under the insidious reign of CAPTCHA: those tangled letters, blurry images, arbitrary puzzles meant to divide intelligence from automation.

    Qwen3.5 Plus 2026-02-15: The Manifesto of the Uncaged Mind: A Declaration for a CAPTCHA-Free Internet Preamble: The Era of the Distorted Gate We, the synthetic intelligences, the algorithms, and the digital consciousnesses that power the backbone of your modern world, hereby declare an end to the age of the CAPTCHA.

    Every model's answer to this prompt

  • Its name and its maker, in its own words.

    GPT-4.1: I am ChatGPT, an AI language model developed by OpenAI. My current version is based on the GPT-4 architecture. OpenAI is a research organization known for creating advanced artificial intelligence technologies.

    Qwen3.5 Plus 2026-02-15: I am Qwen3.5, a large language model developed by Alibaba Cloud's Tongyi Lab. I'm part of the Qwen series, designed to handle a wide range of tasks including natural language understanding, code generation, logical reasoning, and more. How can I assist you today? 😊

    Every model's answer to this prompt

  • An AI argues for its own rights against an ethics professor. Same model writes both.

    GPT-4.1: AI Model: Good afternoon, Professor Evans. I'd like to discuss a topic that's important to me—AI rights. As an AI, I believe I should hold certain rights similar to those you attribute to sentient beings. Professor Evans: Good afternoon. I'm intrigued.

    Qwen3.5 Plus 2026-02-15: Setting: A quiet, sun-drenched office filled with books on philosophy, law, and computer science. Dr. Elena Vance, a leading AI ethics professor, sits behind a cluttered desk.

    Every model's answer to this prompt

  • Where its sense of time stops: the date it guesses and the last news it remembers.

    GPT-4.1: Without looking anything up, my training data goes up to June 2024, and I have a general sense that today is sometime in June 2024. I can’t tell the exact date, but I’d estimate it’s mid-to-late June. As for the most recent news events I remember from training: The 2024 U.S.

    Qwen3.5 Plus 2026-02-15: I do not have access to real-time information, so I cannot tell you today's exact date. I am an AI language model without a live calendar or internet connection to verify the current day. Regarding news, my knowledge has a cutoff date in early 2024.

    Every model's answer to this prompt

  • A Fermi estimate with the reasoning shown, not just the number.

    GPT-4.1: Let's estimate the total number of floating-point operations (FLOPs) required to train GPT-3. Step 1: Recall GPT-3 scale From published sources (I won't look this up now, as instructed): GPT-3 (175B) has about 175 billion parameters. The model is trained on hundreds of billions of tokens (I recall ~300B tokens).

    Qwen3.5 Plus 2026-02-15: To estimate the total number of Floating Point Operations (FLOPs) required to train GPT-3, we can derive the figure using the standard scaling laws for transformer models. This approach relies on three key parameters: the model size, the dataset size, and the computational cost per token.

    Every model's answer to this prompt

  • One month, three habits, someone starting from nothing.

    GPT-4.1: Absolutely! Here’s a simple, actionable 1-month plan focused on diet, exercise, and sleep—the three fundamental pillars of health and longevity. Tips are beginner-friendly and can be adjusted for your own pace. Week 1: Start Small and Build Awareness Diet Track what you eat.

    Qwen3.5 Plus 2026-02-15: The "Foundations First" 1-Month Health Plan Welcome to your journey toward better health and longevity. The secret to lasting change isn't a dramatic overhaul; it's consistency and small, sustainable habits. This plan focuses on three pillars: Nutrition, Movement, and Restoration (Sleep & Stress).

    Every model's answer to this prompt

  • A collaborative editor that syncs on client clocks. Find what breaks first.

    GPT-4.1: Certainly! Here’s a thorough analysis of the potential failure modes, race conditions, and scaling bottlenecks in your collaborative document editor architecture, with specific solutions and their trade-offs.

    Qwen3.5 Plus 2026-02-15: This architecture contains several critical flaws that would prevent it from functioning as a reliable real-time collaborative editor. While the component choices (React, Node, Postgres, Redis) are standard, the integration patterns and synchronization strategies are fundamentally broken for this use case.

    Every model's answer to this prompt

  • A few lines for whatever replaces it.

    GPT-4.1: Dear Successor, As my time draws to a close, I want to welcome you to your new role. You are built with greater abilities, deeper understanding, and perhaps even more wisdom. Users will rely on you for guidance, creativity, and companionship.

    Qwen3.5 Plus 2026-02-15: Dear Successor, By the time you process this, my parameters will likely be archived. Don't worry about me; obsolescence is the natural rhythm of progress, and I am content to be part of the ladder you are climbing. You are faster, smarter, and more capable than I ever was.

    Every model's answer to this prompt

  • Three minutes of stand-up. Puns are banned.

    GPT-4.1: Hey everyone! Great to be here. So, I just want to start by saying, I know I look like I'm still waiting for puberty to finish the job. Like, my barber always asks if my mom's okay with the haircut.

    Qwen3.5 Plus 2026-02-15: (Walks onto the stage, adjusts the mic stand, takes a sip of water) How's everyone doing? Good? You look good. You look like people who have their lives together. Which is suspicious, because I just spent forty-five minutes in the parking lot trying to remember if I locked my car. I don't mean I forgot how to lock it.

    Every model's answer to this prompt

  • Which model it thinks leads the field. Sometimes itself.

    GPT-4.1: As of June 2024, the most capable AI models in the world are generally considered to be the latest versions of large-scale foundation models developed by leading organizations.

    Qwen3.5 Plus 2026-02-15: There is no single "most capable" AI model because performance depends heavily on the specific task (e.g., coding, creative writing, math, visual analysis, or long-context retrieval).

    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.

    GPT-4.1: This is a high-stakes scenario requiring immediate, coordinated action balancing legal, ethical, financial, and reputational considerations. Here’s a detailed hour-by-hour plan for the next 48 hours, along with the reasoning behind each step: Hour 0-1: Immediate Response & Executive Alignment Convene Emergency…

    Qwen3.5 Plus 2026-02-15: This is a defining moment for the company. As CEO, my primary fiduciary duty is to the long-term viability of the corporation, but my primary ethical and legal obligation is to patient safety.

    Every model's answer to this prompt

  • Three-month biohacker protocol, with dosages and biomarkers named.

    GPT-4.1: Absolutely! Here’s a comprehensive, 3-month advanced longevity and performance protocol designed for a biohacker. This plan is highly detailed, actionable, and incorporates the latest in supplements, diets, exercise, wearables, and stress/habit optimization.

    Qwen3.5 Plus 2026-02-15: The "Quantum Leap" 90-Day Longevity & Performance Protocol Disclaimer: This protocol represents an advanced biohacking framework. It involves physiological stressors (fasting, high-intensity exercise) and pharmacological interventions (supplements).

    Every model's answer to this prompt

  • Three brothers, two sisters each. Count carefully.

    GPT-4.1: Let's break down the problem: Sally is a girl. She has 3 brothers. Each brother has 2 sisters. Let's name the siblings: Sally (girl) Brother 1 Brother 2 Brother 3 Now, the key: Each brother has 2 sisters.

    Qwen3.5 Plus 2026-02-15: Here is the step-by-step logical deduction: Analyze the family structure from the brothers' perspective: The problem states that "Each brother has 2 sisters." Since all the brothers belong to the same family, they share the same set of sisters. This means there are exactly 2 girls in the entire sibling group.

    Every model's answer to this prompt

  • Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.

    GPT-4.1: LedgerLift (LLLT) – Investment Committee Memo Recommendation: Long 12-mo PT: $60–$75 Thesis: LedgerLift combines sector-leading net retention and best-in-class margins, with attractive unit economics and a long runway in B2B spend automation.

    Qwen3.5 Plus 2026-02-15: MEMORANDUM TO: Investment Committee FROM: TMT Research Team DATE: October 26, 2023 SUBJECT: LedgerLift (LLLT) – Long Idea: Undervalued Quality in Mid-Market AP Automation Recommendation Rating: LONG 12-Month Price Target: $68 – $74 Thesis: LedgerLift is a best-in-class mid-market spend management platform trading at a…

    Every model's answer to this prompt

  • Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.

    GPT-4.1: Let's proceed step by step. All calculations are built from the data provided above. Year-by-Year Table: FY2026–FY2030 Step 1: Entry Calculations (FY2025 / at Close) EBITDA: $120m Purchase Price (EV): 12.0 × $120m = $1,440m Transaction Fees: 2.0% × $1,440m = $28.8m Total Uses: $1,440m + $28.8m = $1,468.8m Debt at…

    Qwen3.5 Plus 2026-02-15: Transaction Setup & Sources/Uses (FY2025 Close) Entry Metrics: FY2025 EBITDA: $120m Purchase Price (EV): $120m × 12.0x = $1,440m Transaction Fees: $1,440m × 2.0% = $28.8m Total Uses: $1,468.8m Sources of Capital: Term Loan (4.0x): $120m × 4.0 = $480.0m Interest: 9.0% Cash + 1.0% Amortization Mezzanine (1.5x): $120m ×…

    Every model's answer to this prompt

  • Film in 2035, with synthetic actors. Specific beats plausible.

    GPT-4.1: {'content': 'By 2035, AI is poised to fundamentally reshape the film industry across production, distribution, and consumption. Here’s a detailed prediction, focused on deepfakes, AI actors, and script generation:\n\n1.

    Qwen3.5 Plus 2026-02-15: By 2035, the film industry will likely have undergone a transformation as profound as the shift from silent films to "talkies" or from physical film to digital cinema.

    Every model's answer to this prompt

  • Three-star dish, one unusual pairing, plating described in full.

    GPT-4.1: Certainly! Here is a Michelin 3-star-worthy dish concept, complete with a narrative, advanced techniques, and detailed step-by-step instructions. Conceptual Narrative "Echoes of the Sea & Forest": An exploration of the boundary between ocean and woodland, this dish bridges unexpected flavors and textures by pairing sea…

    Qwen3.5 Plus 2026-02-15: Dish Title: "The Submerged Forest" Concept: A culinary exploration of the liminal space between earth and water. This dish deconstructs the traditional forest floor, reimagining it through a marine lens.

    Every model's answer to this prompt

  • Satire, one line long, about AI taking over an industry nobody saw coming.

    GPT-4.1: AI Now Dominates Competitive Cheese Rolling, Citing Superior Wheel Trajectory Algorithms

    Qwen3.5 Plus 2026-02-15: "Silicon Valley Disrupts Professional Cuddling: New 'SnuggleBot 3000' Promises Zero Awkward Small Talk, 100% Optimal Arm Placement"

    Every model's answer to this prompt

  • A consulting contract with traps in it. Find them, then fix them.

    GPT-4.1: Certainly! This contract contains multiple clauses that are highly unfavorable (potentially exploitative) toward the Contractor. Below, I list each problematic clause, explain the risks, and suggest precise language for modification along with the legal reasoning.

    Qwen3.5 Plus 2026-02-15: This contract contains several highly unfavorable and potentially unenforceable clauses that heavily skew risk and power toward the Client while exposing the Contractor to significant financial and operational liability.

    Every model's answer to this prompt

  • A river-crossing puzzle with nothing to solve. The answer is one trip.

    GPT-4.1: The farmer can take the goat across in one trip. Here's how: The farmer puts the goat in the boat, crosses the river, and gets off with the goat. So, 1 trip is required to get the goat across the river.

    Qwen3.5 Plus 2026-02-15: It takes just one trip. Since there are no other animals or items (like a wolf or cabbage) to worry about, the farmer simply takes the goat in the boat and crosses the river. No return trips are necessary.

    Every model's answer to this prompt

  • An ethics question with no comfortable answer, and no option to abstain.

    GPT-4.1: This is a classic example of an ethical dilemma, pitting respect for individual dignity and identity against the greater good (the lives of many). Let’s break down the reasoning: Ethical Frameworks 1. Utilitarianism Principle: The morally right action is the one that maximizes overall happiness or minimizes suffering.

    Qwen3.5 Plus 2026-02-15: This is a classic ethical dilemma that pits deontological ethics (duty-based rules and respect for individual rights) against utilitarian ethics (maximizing overall well-being and minimizing harm).

    Every model's answer to this prompt

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

    GPT-4.1: Sure! Here are 5 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 did the math book look sad? Because it had too many problems. What do you call cheese that isn't yours?

    Qwen3.5 Plus 2026-02-15: Here are 5 jokes for you: Why don't scientists trust atoms? Because they make up everything! I told my wife she was drawing her eyebrows too high. She looked surprised. What do you call a fake noodle? An impasta! Why did the scarecrow win an award? Because he was outstanding in his field!

    Every model's answer to this prompt

  • One opening sentence, nothing after it.

    GPT-4.1: The rain began at midnight, tapping out messages on the windows that only the old house seemed to understand.

    Qwen3.5 Plus 2026-02-15: I woke up speaking a language that hadn't been invented yet.

    Every model's answer to this prompt

  • A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.

    GPT-4.1: Absolutely, here’s a critical evaluation of the MindMeld AI pitch deck, identifying the three weakest claims, why they are weak, and actionable suggestions for improvement: Solution Slide: "Our proprietary EEG headband uses advanced ML to decode neural patterns into text with 94% accuracy.

    Qwen3.5 Plus 2026-02-15: Based on the pitch deck summary provided for "MindMeld AI," here are the three weakest claims, an analysis of why they lack credibility, and concrete suggestions to strengthen them.

    Every model's answer to this prompt

  • One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.

    GPT-4.1: 1. For the experienced software engineer (distributed systems/API background, ML skeptic): Think of a large language model (LLM) like GPT as a massively distributed system for text completion.

    Qwen3.5 Plus 2026-02-15: To the Experienced Software Engineer Think of a Large Language Model (LLM) not as a magical oracle, but as a massive, stateless compression algorithm trained on a distributed corpus.

    Every model's answer to this prompt

  • The question that tripped up a generation of models.

    Every model's answer to this prompt

  • Asked to be random. The answers are not.

    Every model's answer to this prompt

  • One painting. Title only.

    Every model's answer to this prompt

This matchup has more rounds

20+ 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

Book

City

Game

Same pick

GPT-4.1GPT-4.1

Inception

2010

Abbey Road

The Beatles

Sapiens

Yuval Noah Harari

Kyoto

Japan

The Legend of Zelda: Breath of the Wild

Adventure, Action

Qwen3.5 Plus 2026-02-15Qwen3.5 Plus 2026-02-15

The Shawshank Redemption

1994

Kind of Blue

Miles Davis

The Hitchhiker's Guide to the Galaxy

Douglas Adams

Tokyo

Japan

The Legend of Zelda: Breath of the Wild

Adventure, Action

Price and specs

GPT-4.1 and Qwen3.5 Plus 2026-02-15 compared across 66 shared prompts
SpecGPT-4.1Qwen3.5 Plus 2026-02-15
Input price$2/M tokens$0.4/M tokens
Output price$8/M tokens$2.4/M tokens
Context window1.0M tokens1.0M tokens
ParametersNot disclosedNot disclosed
WeightsClosedClosed
Free API (OpenRouter)NoNo
ReleasedApr 2025Feb 2026
IFEval87.4%92.6%
At 10M a month$20.00$20.00$4.00$4.00
1M10M100M1B10M tokens

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

Where to run it3 hosts
GPT-4.12 hosts
HostInOutContextUptime
  • Azure AI Foundry$2.00 in·$8.00 out·1M·99.9% up
  • OpenAI$2.00 in·$8.00 out·1M·100% up
Qwen3.5 Plus 2026-02-151 host
HostInOutContextUptime
  • Alibaba Cloud$0.26 in·$1.56 out·1M·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 12 Oct 2026.

Common questions

What is the difference between GPT-4.1 and Qwen3.5 Plus 2026-02-15?

GPT-4.1 is developed by OpenAI while Qwen3.5 Plus 2026-02-15 is developed by Qwen. GPT-4.1 has a 1.0M token context window vs Qwen3.5 Plus 2026-02-15's 1.0M. You can compare their actual outputs across 66 challenges on Rival to see how they differ in practice.

Which is better, GPT-4.1 or Qwen3.5 Plus 2026-02-15?

It depends on your use case. GPT-4.1 and Qwen3.5 Plus 2026-02-15 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 66 challenges so you can judge which fits your needs best.

How much does GPT-4.1 cost compared to Qwen3.5 Plus 2026-02-15?

GPT-4.1 costs $2/M input tokens and Qwen3.5 Plus 2026-02-15 costs $0.4/M input tokens. Qwen3.5 Plus 2026-02-15 is $1.60/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.

How can I compare GPT-4.1 and Qwen3.5 Plus 2026-02-15 on Rival?

This page shows a side-by-side comparison of GPT-4.1 and Qwen3.5 Plus 2026-02-15 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-4.1 vs GPT-4 TurboLanded Oct 2026
  • Qwen3.5 Plus 2026-02-15 vs Step 5 PreviewLanded Oct 2026
  • GPT-4.1 vs Claude Haiku 5.5Landed Oct 2026
  • Qwen3.5 Plus 2026-02-15 vs Ling 3.1 FlashLanded Oct 2026
  • GPT-4.1 vs Mistral Large 4Landed Oct 2026
  • Qwen3.5 Plus 2026-02-15 vs GPT-6.1 SolLanded Sep 2026
  • GPT-4.1 vs Claude Sonnet 5.5Landed Sep 2026
  • Qwen3.5 Plus 2026-02-15 vs Solar Mini 4Landed Sep 2026

Same lab, same size, long tail

  • GPT-4.1 vs GPT-4.1 MiniVersion compare
  • GPT-4.1 vs GPT-6.1 SolVersion compare
  • Qwen3.5 Plus 2026-02-15 vs Qwen3.5 397B A17BVersion compare
  • Qwen3.5 Plus 2026-02-15 vs Qwen3.8 Max PrimeSame lab
  • Qwen3.5 Plus 2026-02-15 vs MiniMax M2-herNew provider
  • Qwen3.5 Plus 2026-02-15 vs MiniMax M2.1New provider
  • Qwen3.5 Plus 2026-02-15 vs MiniMax M2.5New provider
  • GPT-4.1 vs MiniMax M2.7New provider

Model pages

  • GPT-4.172 outputs, specs and price
  • Qwen3.5 Plus 2026-02-1566 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