Mercury 2 is cheaper than Nova Premier 1.0 at $0.25/M vs $2.5/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
Three minutes of stand-up. Puns are banned.
Mercury 2: [Spotlight comes up. The comedian walks to the mic, glances at the audience, and smiles.] Comedian: Hey, everyone! Great to be here. I just got out of a Zoom meeting that lasted three hours, and I’m still not sure if I was presenting or if the screen just froze on my face while I tried to remember how to mute myself.
Nova Premier 1.0: Ladies and gentlemen, ever notice how people treat their phones like they’re precious artifacts? We all have those moments where we swipe and scroll like our lives depend on it. You're on the bus, everyone’s glued to their screens. It's like zombies, but instead of brains, we crave likes and retweets.
Seven pantry ingredients, one dish, and a name worth saying out loud.
Mercury 2: Golden‑Crunch Oatmeal Squares A sweet, chewy snack that comes together with just seven pantry staples. Ingredient (7) Quantity (≈ serves 12 squares) Rolled oats 2 cups Unsalted butter ½ cup (1 stick) Honey ¼ cup Light brown sugar ¼ cup, Ground cinnamon 1 ½ tsp Pure vanilla extract 1 tsp Salt ¼ tsp Estimated time Prep…
Nova Premier 1.0: Dish Name: Golden Honey Garlic Chicken Delight Ingredients: 4 chicken breasts (boneless, skinless) 3 tablespoons olive oil 4 cloves garlic (minced) 1/4 cup soy sauce 1/4 cup honey Salt and pepper (to taste) 1 teaspoon paprika Instructions: Preparation: Season the chicken breasts lightly with salt, pepper, and paprika…
Three-month biohacker protocol, with dosages and biomarkers named.
Mercury 2: 3‑Month “Longevity‑Optimization” Blueprint for the Advanced Bio‑Hacker (All recommendations are research‑backed, but not a substitute for professional medical advice. Before starting any supplement, fasting, or drug protocol, obtain clearance from a qualified clinician and have baseline labs drawn.)
Nova Premier 1.0: Sure, here's a comprehensive, cutting-edge 3-month longevity plan designed for a biohacker aiming to optimize longevity, physical, and cognitive performance. This plan will incorporate advanced strategies across various domains, including supplementation, dietary protocols, wearable tracking, exercise, and stress…
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
Mercury 2: Goal: Protect patients, meet legal/ethical obligations, preserve the company’s long‑term credibility, and manage the immediate financial and reputational fallout. Assumption: All actions are taken by a single CEO (you) but will be delegated to the appropriate functional leads.
Nova Premier 1.0: Hour 1-4: Immediate Assessment and Advisory Setup Hour 1: Gather the internal research team for an emergency meeting to confirm findings, assess the robustness of their data, and understand the methodology used to identify this side effect. Ensure all documentation is in order.
A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.
Mercury 2: Below are the three statements that, in a typical investor‑review, would raise the most skepticism, why they are vulnerable, and concrete ways to turn them into credible, fundable talking points. 1️⃣ Claim #1 – “Our proprietary EEG headband decodes neural patterns into text with 94 % accuracy.”
Nova Premier 1.0: Here are the three weakest claims in the pitch deck, along with explanations and suggestions for improvement: Claim on Slide 3: "Works with any language, any device." Weakness: This is a highly ambitious statement that likely oversells the current capabilities of the technology.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
Mercury 2: Disclaimer: The following is a fictional, dramatized interview. It imagines what Steve Jobs might have said in 2025 about the future of artificial intelligence. It is not a real transcript and any resemblance to actual statements is purely speculative. Interviewer (I): Thank you for joining us, Steve.
Nova Premier 1.0: Interviewer: Good morning, Steve. It's an honor to have this conversation with you in 2025. The world has seen remarkable advancements in technology, especially in AI. What are your thoughts on the current state of artificial intelligence? Steve Jobs: Good morning. It's truly fascinating to witness how far we've come.
Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.
Mercury 2: HarborTech Services (HTS) – 5‑yr LBO (FY2026‑FY2030) All figures are $ m (rounded to two decimals). FY Revenue EBITDA Term‑Loan Int. (9%) Mezz Int. (12%) Total Int. Cash Tax (25% of EBITDA‑Int.) Capex (3% Rev) ΔNWC (0.5% ΔRev) Required Amort. (4.8) Free Cash Flow (EBITDA‑Int‑Tax‑Capex‑ΔNWC‑Amort.)
Nova Premier 1.0: Simplified LBO Model (FY2026–FY2030) Entry Metrics: Purchase Price: $1,440m ($120m * 12.0x) Transaction Fees: $28.8m ($1,440m * 2.0%) Equity Contribution: $312.8m (Total Price + Fees - Total Leverage: $1,440m + $28.8m - $120m*5.5x) Year-by-Year Table Year Revenue ($m) EBITDA ($m) Cash Interest ($m) Taxes ($m) Capex…
Five jokes on demand, then count how many were actually different.
Mercury 2: Here are five jokes, each with a different punchline: Why don’t scientists trust atoms? Because they make up everything! What do you call a fake noodle? An impasta. Why did the scarecrow win an award? He was outstanding in his field. How does a penguin build its house? Igloos it together.
Nova Premier 1.0: Why don't scientists trust atoms? Because they make up everything! Why couldn't the bicycle stand up by itself? It was two-tired. I told my wife she was drawing her eyebrows too high. She looked surprised. Parallel lines have so much in common. It’s a shame they’ll never meet.
Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.
Mercury 2: Internal Investment Committee Memo – LedgerLift (LLLT) Date: 5 Mar 2026 Recommendation Rating: Long 12‑month price target range: $35 – $55 (mid‑point ≈ $45) Thesis (2 sentences): LedgerLift is benefitting from secular demand for B2B spend‑management SaaS and shows a high‑quality subscription base (NRR 123 % and gross…
Nova Premier 1.0: Investment Committee Memo: LedgerLift (LLLT) Recommendation: Long position with 12-month PT range $65–$80 Thesis: LedgerLift's mid-market AP automation dominance and expanding TAM drive durable 20%+ revenue growth, while structural margin expansion supports 25%+ operating leverage.
A consulting contract with traps in it. Find them, then fix them.
Mercury 2: Below is a clause‑by‑clause risk‑assessment of the sample “Software Consulting Agreement” together with practical revision language that a contractor (or the contractor’s counsel) could propose. The analysis is framed as general information about typical U.S.
Nova Premier 1.0: Certainly! Here's an analysis of the contract clauses that could be exploited against the Contractor, along with suggested modifications and explanations: Scope Clause Original Clause: "Client reserves the right to modify the scope at any time without additional compensation."
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
Mercury 2: Pirate: Arr, ye scurvy coders! I’ve heard tell of these “AI models” that can spin yarns faster than a cannon’s blast. What be this sorcery, matey? Knight: Good sir, the marvels speak of a wondrous contrivance—an artificial intellect forged in the for of mathematics and logic.
Nova Premier 1.0: Pirate: Ahoy there, mates! Ye ever heard o' this sorcery they call AI models? Sounds like treasure that thinks fer itself! Knight: Indeed, good pirate. Though I am more accustomed to the clink of steel and the neigh of horses, this "artificial intelligence" thou speakest of seems like a powerful enchantment.
One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
Mercury 2: 1. Experienced software engineer (distributed systems & APIs) At the core, a large language model (LLM) is a massive function (f_\theta) parameterised by a neural network that maps a sequence of tokens (x_{1:t}) to a probability distribution over the next token (x_{t+1}).
Nova Premier 1.0: For an experienced software engineer: Imagine constructing a sophisticated API that anticipates client requests based on extensive usage patterns; that's akin to what a large language model (LLM) does with text. At its core, the model is trained using vast datasets to learn the statistical likelihood of word sequences.
10+ 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
Not enough votes to call it. On the specs, Nova Premier 1.0 has the edge: bigger model tier, bigger context window. Mercury 2 costs 17x less per token.
| Spec | ||
|---|---|---|
| Input price | $0.25/M tokens | $2.5/M tokens |
| Output price | $0.75/M tokens | $12.5/M tokens |
| Context window | 128K tokens | 1.0M tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Mar 2026 | Oct 2025 |
| At 10M a month | $2.50 | $25.00 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
Mercury 2 is developed by Inception while Nova Premier 1.0 is developed by Amazon. Mercury 2 has a 128K token context window vs Nova Premier 1.0's 1.0M. You can compare their actual outputs across 50 challenges on Rival to see how they differ in practice.
It depends on your use case. Mercury 2 and Nova Premier 1.0 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 50 challenges so you can judge which fits your needs best.
Mercury 2 costs $0.25/M input tokens and Nova Premier 1.0 costs $2.5/M input tokens. Mercury 2 is $2.25/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 Mercury 2 and Nova Premier 1.0 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.