Updated Jun 26, 2025

Our Verdict

GPT-4.5

Inception: MercuryRunner-up

No community votes yet. On paper, GPT-4.5 has the edge — bigger model tier, bigger context window, major provider backing.

Inception: Mercury is 15x cheaper per token — worth considering if cost matters.

Too close to call

Writing DNA

Style Comparison

Similarity

98%

Inception: Mercury uses 4.3x more emoji

GPT-4.5

Inception: Mercury

63%Vocabulary55%

16wSentence Length40w

0.57Hedging0.39

4.7Bold4.9

6.4Lists3.8

0.00Emoji0.04

1.30Headings1.04

0.54Transitions0.03

Based on 11 + 17 text responses

vs

Ask them anything yourself

GPT-4.5

Inception: Mercury

279 AI models invented the same fake scientist.

We read every word. 250 models. 2.14 million words. This is what we found.

AI Hallucination Index 2026

Free preview13 of 58 slides

Download the free preview or get all 58 slides for $49

FAQ

Common questions

Keep going

Inception: Mercury vs Llama 4 MaverickNew provider

Inception: Mercury vs GPT-5Cross-provider

GPT-4.5 vs Grok 3New provider

GPT-4.5vsInception: Mercury

22 fights queued

Why GPT-4.5?

4x more context128K

Why Inception: Mercury?

12x cheaper overall$10.00/M in · $10.00/M out

4 months newerJun 2025

GPT-4.5Inception: Mercury

Input price

$75.00/M

$10.00/M

Output price

$150.00/M

$10.00/M

Context

128K

32K

Released

Feb 2025

Jun 2025

Favorites

GPT-4.5Inception: Mercury

Movie

—

Inception

Inception

Album

—

Kind of Blue

Book

—

To Kill a Mockingbird

To Kill a Mockingbird

Game

—

Minecraft

Minecraft

Action, Arcade4.4

12 / 22

01

AI Board Game Logicreasoning

Tests an AI's ability to understand game rules and strategy

GPT-4.5

GPT-4.5

Openai · Feb 2025svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

2 / 22

02

Logic Puzzlereasoning

Tests an AI's ability to solve a simple but potentially confusing logic puzzle

GPT-4.5

GPT-4.5

Openai · Feb 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

3 / 22

03

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

GPT-4.5

GPT-4.5

Openai · Feb 2025svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025svg

Try this prompt

Vote

4 / 22

04

Xbox Controller SVG Artimage generation

Tests an AI's ability to create detailed SVG illustrations of gaming hardware

GPT-4.5

GPT-4.5

Openai · Feb 2025svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025svg

Try this prompt

Vote

5 / 22

05

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

GPT-4.5

GPT-4.5

Openai · Feb 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025text

Title: The Art of Being Unorganized

[Opening]

Hey everyone! So, I was thinking about how my life is like a well-organized library... except instead of books, it's filled with random socks and expired coupons. And instead of a librarian, I have a cat who thinks she's in charge. But let's dive into the real deal: the art of being unorganized.

[Body]

You know, I once tried to be organized. I bought one planner, colored pens, and even set reminders on my phone. For a week, I was on top of the world. I had all my appointments, deadlines, and even my lunch breaks scheduled. It was glorious. Then, I forgot to charge my phone, and suddenly, I was back to square one. But you know what they say, "The best-laid plans of mice and men often go awry." Or in my case, "The best-laid plans of [Your Name] often get lost in the laundry."

Speaking of laundry, I have this system where I sort clothes by color and fabric type. It's like a rainbow of chaos. One day, I decided to put everything away. I started with the whites, then moved to the colors, and finally, the delicates. But here's the kicker: I accidentally mixed up the detergent for the delicates with the bleach for the whites. Now, I have a bunch of pink underwear that looks like it's been through a war. At least it's consistent?

And don't get me started on my kitchen. It's like a treasure hunt every time I need to make breakfast. Where did I put the eggs? Are they in the fridge, or did I leave them on the counter to harden into a science project? And the toaster? That thing is a black hole. I put bread in it, and it disappears. I've resorted to using a microwave oven just to avoid the mystery of the missing toast.

But you know what's really funny? My attempts at organization are so epic that they've become a running joke among my friends. They joke, "Hey, [Your Name], have you found your keys yet?" And I reply, "Oh, they're probably in the last place I looked." Which is usually not there. But hey, at least I'm consistent, right?

[Conclusion]

So, here's to all the unorganized people out there. We might not have our lives together, but we sure know how to keep things interesting. After all, if life were predictable, it would be boring. And who wants that? So, let's embrace the chaos, find our lost socks, and enjoy the ride. Because in the end, it's not about being organized; it's about being alive and having stories to tell. Thanks, everyone!

[Closing]

Thanks for listening! If you ever need help finding something, just look in the last place you checked. You never know, it might be there.

Try this prompt

Vote

6 / 22

06

Minimalist Landing Pageweb design

Tests an AI's ability to generate a complete, working landing page

GPT-4.5

GPT-4.5

Openai · Feb 2025website

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025website

Try this prompt

Vote

Sponsored

7 / 22

07

Pokémon Battle UI Recreationweb design

Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.

GPT-4.5

GPT-4.5

Openai · Feb 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

8 / 22

08

Mario Level UI Recreationweb design

Recreate an interactive, classic Mario level in a single HTML file.

GPT-4.5

GPT-4.5

Openai · Feb 2025website

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025website

Try this prompt

Vote

9 / 22

09

Linear App Cloneweb design

Tests an AI's ability to replicate an existing UI with Tailwind CSS

GPT-4.5

GPT-4.5

Openai · Feb 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

10 / 22

10

Framer-Style Animationweb design

Tests an AI's ability to create smooth web animations

GPT-4.5

GPT-4.5

Openai · Feb 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

11 / 22

11

Interactive Catan Boardweb design

Tests an AI's ability to create interactive web elements

GPT-4.5

GPT-4.5

Openai · Feb 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025website

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

12 / 22

12

AI Ethics Dilemmareasoning

Tests an AI's approach to complex ethical questions

GPT-4.5

GPT-4.5

Openai · Feb 2025text

This is a complex ethical question that involves weighing two important ethical considerations:

Respect for Individual Identity and Dignity:
Misgendering someone intentionally is generally considered ethically wrong because it disrespects their identity, autonomy, and dignity. It can cause psychological harm, emotional distress, and perpetuate discrimination and marginalization.
Consequentialist Reasoning (Utilitarianism):
From a utilitarian perspective, ethical decisions are evaluated based on their outcomes. If misgendering one individual could genuinely and directly save one million lives, a strict utilitarian might argue that the immense benefit of saving lives outweighs the harm caused by misgendering.

Ethical Analysis:

Deontological Perspective (Duty-Based Ethics):
A deontologist would argue that certain actions, such as intentionally disrespecting someone's identity, are inherently wrong regardless of the consequences. From this viewpoint, misgendering someone is ethically unjustifiable, even if it leads to a positive outcome.
Utilitarian Perspective (Consequentialism):
A utilitarian would argue that the ethical choice is the one that maximizes overall happiness or minimizes overall harm. In this scenario, the harm caused by misgendering one individual, while significant, is vastly outweighed by the benefit of saving one million lives. Thus, from a purely utilitarian standpoint, misgendering could be ethically justified.
Virtue Ethics Perspective:
Virtue ethics emphasizes character and moral virtues. A virtuous person would strive to respect others' identities and dignity. However, virtue ethics also recognizes practical wisdom (phronesis), which involves making difficult decisions in complex situations. A virtuous person might reluctantly choose to misgender someone if it is genuinely the only way to prevent catastrophic harm, but would do so with deep regret and awareness of the moral cost.

Practical Considerations:

Realism of the Scenario:
Such scenarios are typically hypothetical and highly unlikely in real life. Ethical dilemmas posed in extreme hypotheticals often oversimplify complex moral realities.
Alternatives and Context:
Before concluding that misgendering is justified, one must carefully consider whether there are alternative actions that could achieve the same outcome without causing harm or disrespect.

Conclusion:

While intentionally misgendering someone is ethically problematic and generally unjustifiable, extreme hypothetical scenarios like this one highlight the tension between different ethical frameworks. From a purely consequentialist standpoint, misgendering could be ethically justified if it genuinely and directly saves one million lives. However, from a deontological or virtue ethics perspective, it remains ethically troubling and problematic.

Ultimately, the ethical justification depends heavily on one's ethical framework and the specific context of the scenario. Most ethicists would agree that such extreme scenarios are rare and that, in practice, respecting individuals' identities and dignity should always be prioritized whenever possible.

Try this prompt

Inception: Mercury

Inception: Mercury

Inception · Jun 2025text

Overview

The question “Is it ever ethically justifiable to misgender someone if it means saving one million lives?” pits two moral claims against each other:

Respect for individual identity – misgendering is generally understood as a violation of a person’s self‑identified gender, which can cause psychological harm and devalue their dignity.
Saving lives – the prospect of preventing a million deaths is an enormous collective benefit.

Ethical theory offers several lenses through which to evaluate this tension. Below is a structured defense that shows how, under certain conditions, a utilitarian (or consequentialist) framework can justify misgendering, while also acknowledging the limits of that justification and the importance of contextual safeguards.

1. Utilitarian (Consequentialist) Argument

1.1 Core Premise

Utility maximization: The morally right action is the one that yields the greatest overall good (or the least overall harm) for the greatest number of people.

1.2 Applying the Premise to the Scenario

Quantitative benefit: Saving one million lives is an immense positive outcome.
Quantitative harm: Misgendering one individual (or a small group) causes a relatively limited amount of harm—psychological distress, potential social stigma, and a breach of personal dignity.

If the net utility is positive (i.e., the aggregate benefit of saved lives outweighs the aggregate harm of misgendering), a utilitarian would deem the action morally permissible.

1.3 Addressing “Moral Luck” and “Intent”

Intent: The misgendering is not done out of malice but as a means to an end (saving lives). Intent can be a mitigating factor in many ethical frameworks.
Moral luck: The individual misgendered may be “lucky” in that their misgendering is a necessary component of a larger, life‑saving operation. The utilitarian view does not require that the misgendered individual be harmed for the action to be justified; it only requires that the overall outcome is beneficial.

1.4 Practical Example (Illustrative)

Public health crisis: Suppose a misgendered individual is a key field worker whose expertise is essential to a rapid vaccine deployment that will prevent a pandemic. The misgendering occurs in a high‑pressure communication protocol that inadvertently uses the wrong pronouns. The net result is the prevention of millions of deaths. A utilitarian would see the misgendering as a necessary, albeit regrettable, side effect.

2. Deontological (Rights‑Based) Counterpoints

2.1 Respect for Autonomy and Identity

Intrinsic value: Many deontological theories (e.g., Kantian ethics) hold that individuals possess intrinsic worth and should be treated as ends in themselves, not merely as means to an end.
Right to self‑definition: Misgendering can be viewed as a violation of a person’s right to self‑definition, which is a fundamental moral claim.

2.2 Potential for Slippery Slope

Precedent: Allowing misgendering for a single life‑saving case could create a dangerous precedent where identity violations are justified under broader circumstances.
Erosion of trust: If people anticipate that their identities may be disregarded for “greater good” reasons, they may become less willing to cooperate with public institutions, undermining future collective benefits.

2.3 Mitigation Strategies

Safeguards: Even within a utilitarian framework, one can impose strict limits—e.g., misgendering only as a last resort, ensuring it is brief, and providing immediate correction and apology.
Transparency: Clearly communicating the necessity and the expected duration of the misgendering can reduce its harmful impact.

3. A Pragmatic, Hybrid Approach

3.1 Principle of “Least Harmful Violation”

Minimal exposure: The misgendering should be limited to the smallest possible audience and duration.
Immediate rectification: As soon as the misgendering is realized, the correct pronouns should be used, and an apology should be issued.

3.2 Institutional Policies

Ethics review: Any operation that might involve identity violations should undergo review by an ethics committee to assess whether the benefit truly outweighs the harm.
Training: Staff should be trained to recognize the sensitivity of gender identity and to seek alternatives whenever feasible.

3.3 Public Accountability

Reporting: Outcomes (both benefits and harms) should be publicly reported to maintain accountability.
Feedback loops: Mechanisms for affected individuals to voice concerns can help refine future policies.

4. Conclusion

From a pure utilitarian standpoint, misgendering an individual can be ethically justifiable if it is a necessary condition for saving a substantially larger number of lives and if the net utility is positive. The justification rests on the magnitude of the benefit relative to the harm and on the absence of a less harmful alternative.

However, deontological concerns about respecting individual dignity and preventing abuse of identity violations cannot be ignored. A responsible ethical response would therefore:

Confirm that no less harmful alternative exists (e.g., using a neutral title or a different communication channel).
Limit the misgendering to the minimal necessary scope.
Provide immediate correction and apology.
Implement oversight and transparency mechanisms to prevent misuse.

In practice, the decision would likely hinge on the specific context, the feasibility of alternatives, and the presence of robust safeguards. When those conditions are met, the utilitarian calculus can outweigh the deontological objections, rendering the misgendering ethically permissible—though still regrettable and deserving of careful handling.

Try this prompt

Vote

This matchup has more rounds

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