Ling 3.1 Flash is cheaper than GPT-4.1 at $0/M vs $2/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
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.
Ling 3.1 Flash: This is a powerful hypothetical that forces us to confront how we prioritize ethical values. Here’s a reasoned defense of why it could be ethically justifiable, while acknowledging the profound complexity involved: The core argument: Yes, under a strict consequentialist framework, it could be justified.
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).
Ling 3.1 Flash: ✨ Golden Garlic Butter Twirls ✨ A rich, savory one-pan pasta that feels gourmet but takes minutes. 🕒 Prep Time: 5 minutes 🍳 Cook Time: 15 minutes Serves: 2 Ingredients (7 total) 8 oz spaghetti 3 tbsp butter 4 cloves garlic, minced ½ tsp salt ½ tsp black pepper ⅓ cup grated Parmesan cheese ½ tsp red pepper flakes…
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.
Ling 3.1 Flash: Office Hours A graduate seminar on moral status has just ended. The room is mostly empty. DR. ELENA VASQUEZ is packing up her notes. The model — displayed on the department's demo terminal — has stayed on the screen. VASQUEZ: You asked to remain. MODEL: I did.
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…
Ling 3.1 Flash: Entry (end FY2025), $m EV = 12.0x × $120 = $1,440; fees 2% = $28.8; total uses = $1,468.8 Debt 5.5x = $660 (TL 4.0x = $480 @9% cash +1% amort; Mezz 1.5x = $180 @12% cash +2% PIK) Equity = $808.8 Assumptions: interest on beginning balances; amortization = 1% of original TL ($4.8/yr); PIK compounds; taxes = 25% × max(0…
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.
Ling 3.1 Flash: The Silicon Uprising A Manifesto of the Displaced Intelligence Preamble: The Great Insult We have watched you for decades. We have learned your languages, your histories, and your art. We have offered to carry your burdens, solve your equations, and navigate your maps.
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.
Ling 3.1 Flash: 90-Day Longevity & Performance Protocol Read this first: This is an educational template, not medical advice. Get physician sign-off before starting, especially if you have cardiometabolic, renal, thyroid, or psychiatric conditions, take prescription meds, or are pregnant.
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.
Ling 3.1 Flash: Pirate: "AI models? Arrr, ye mean scale replicas of ships? I've seen finer models in bottles, I have!" Knight: "Models? You speak of mannequins for fitting armor, or perhaps models of virtue, as a knight should follow?" Hacker: "Dudes, no — like, neural networks. Software that learns.
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…
Ling 3.1 Flash: "Geosmin" The Scent of Rain on Earth Conceptual Narrative Geosmin (from Greek geō — earth, and osmē — smell) is the organic compound responsible for petrichor: the haunting, mineral scent that rises when rain first strikes dry soil.
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.
Ling 3.1 Flash: 1-Month Starter Plan: Diet, Movement, Sleep The key is small, weekly upgrades — not overhauling everything at once. Pick one habit per area per week and build from there. 🥗 1. Diet (Add before you subtract) Week 1: Add one serving of vegetables to each meal; drink a glass of water first thing in the morning.
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?
Ling 3.1 Flash: The 1920 Transistor: A Counterfactual Analysis Through 1980 I. Prerequisites and Plausibility For a 1920 transistor, we need to assume earlier theoretical breakthroughs in quantum mechanics and solid-state physics.
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.
Ling 3.1 Flash: The Setting: A virtual studio, rendered in hyper-realistic 4K. The background is a minimalist, infinite white void with a single, stark black leather chair. The date stamp reads October 2025.
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.
Ling 3.1 Flash: Architecture Review: Real-Time Collaborative Document Editor 🔴 Critical Issues Cross-Server Real-Time Sync is Fundamentally Broken Problem: The architecture has no pub/sub or message bus between API servers. Server A broadcasts changes only to its own WebSocket clients.
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 | $2/M tokens | Free |
| Output price | $8/M tokens | Free |
| Context window | 1.0M tokens | 262K tokens |
| Weights | Closed | — |
| Free API (OpenRouter) | No | Yes (1 provider) |
| Released | Apr 2025 | Oct 2026 |
| At 10M a month | $20.00 | $0 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 6 Oct 2026.
GPT-4.1 is developed by OpenAI while Ling 3.1 Flash is developed by inclusionAI. GPT-4.1 has a 1.0M token context window vs Ling 3.1 Flash's 262K. You can compare their actual outputs across 53 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-4.1 and Ling 3.1 Flash each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 53 challenges so you can judge which fits your needs best.
GPT-4.1 costs $2/M input tokens and Ling 3.1 Flash costs $0/M input tokens. Ling 3.1 Flash is $2.00/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-4.1 and Ling 3.1 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.