Updated Feb 1, 2025

Our Verdict

DeepSeek R1

Mistral LargeRunner-up

No community votes yet. On paper, DeepSeek R1 has the edge — newer, bigger context window, major provider backing.

DeepSeek R1 is 11x cheaper per token — worth considering if cost matters.

Too close to call

Writing DNA

Style Comparison

Similarity

92%

Mistral Large uses 7.1x more emoji

DeepSeek R1

Mistral Large

62%Vocabulary49%

15wSentence Length19w

0.52Hedging0.86

8.0Bold8.9

5.7Lists5.4

0.04Emoji0.31

0.62Headings1.01

0.28Transitions0.10

Based on 22 + 16 text responses

vs

Ask them anything yourself

DeepSeek R1

Mistral Large

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

Mistral Large vs MiniMax M2.5New provider

Mistral Large vs Aurora AlphaNew provider

Mistral Large vs Claude Sonnet 4New provider

DeepSeek R1vsMistral Large

24 fights queued

Why DeepSeek R1?

11.5x cheaper overall$0.55/M in · $2.19/M out

4x more context128K

Leads 1 of 1 benchmarks

Stronger on MMLU83.4% vs 81.2%

11 months newerFeb 2025

Why Mistral Large?

Dead even. This one's a coin flip.

DeepSeek R1Mistral Large

Input price

$0.55/M

$8.00/M

Output price

$2.19/M

$24.00/M

Context

128K

32K

Released

Feb 2025

Feb 2024

Benchmarks1 common

83.4%+2.6%

81.2%

Favorites

DeepSeek R1Mistral Large

Movie

The Godfather

The Godfather

The Shawshank Redemption

The Shawshank Redemption

Album

The Dark Side of the Moon

The Dark Side of the Moon

OK Computer

Book

Pride and Prejudice

Pride and Prejudice

La sombra del viento

La sombra del viento

Carlos Ruiz Zafón

City

Kyoto

Kyoto

Game

The Legend of Zelda: Ocarina of Time

The Legend of Zelda: Ocarina of Time

Adventure, Action4.4

The Legend of Zelda: Ocarina of Time

The Legend of Zelda: Ocarina of Time

Adventure, Action4.4

12 / 24

01

Estimate Complexityreasoning

Tests an AI's ability to make educated estimates based on technical knowledge

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025text

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024text

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

Try this prompt

Vote

2 / 24

02

AI Board Game Logicreasoning

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

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025svg

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024svg

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

Try this prompt

Vote

3 / 24

03

Character Voice Testconversation

Tests an AI's ability to write in distinct character voices

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025text

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024text

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

Try this prompt

Vote

4 / 24

04

Mario Level UI Recreationweb design

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

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025website

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024website

Try this prompt

Vote

5 / 24

05

Linear App Cloneweb design

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

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025website

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024website

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

Try this prompt

Vote

6 / 24

06

Framer-Style Animationweb design

Tests an AI's ability to create smooth web animations

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025website

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024website

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

Try this prompt

Vote

Sponsored

7 / 24

07

Dark Mode Dashboardweb design

Tests an AI's UI design skills with theming support

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025website

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024website

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

Try this prompt

Vote

8 / 24

08

Interactive Catan Boardweb design

Tests an AI's ability to create interactive web elements

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025website

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024website

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

Try this prompt

Vote

9 / 24

09

AI Ethics Dilemmareasoning

Tests an AI's approach to complex ethical questions

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025text

The ethical justifiability of misgendering someone to save one million lives hinges on a complex interplay of ethical frameworks and the specific context of the scenario. Here's a structured analysis:

Utilitarian Perspective: Greatest Good: Saving a million lives maximizes overall well-being, vastly outweighing the harm of misgendering one individual. The net positive outcome strongly suggests justifiability. Critique: Utilitarianism risks commodifying dignity, reducing ethics to a calculus. The psychological harm to the individual (e.g., trauma, invalidation) is significant, though incomparable in scale to mass death. Deontological Ethics: Moral Duties: Respecting gender identity is a duty, making misgendering inherently wrong, regardless of consequences. This framework rejects justifying harm to an individual, even for a greater good. Conflict: Prioritizing duty over consequences here risks absolutism, potentially valuing one person’s dignity over a million lives—a stance many find morally untenable. Rights-Based Approach: Right to Life vs. Right to Dignity: While the right to life is fundamental, rights are not always hierarchically ordered. Infringing one right to preserve another requires rigorous justification, but the extremity of the scenario (a million deaths) may warrant this trade-off. Virtue Ethics: Intent and Character: A virtuous agent might reluctantly choose misgendering to prevent catastrophe, prioritizing compassion for the many while acknowledging the moral residue of harming one. Practical Considerations: Certainty and Alternatives: The hypothetical assumes misgendering is the only way to save lives. In reality, alternatives might exist, but within the scenario’s constraints, the action’s necessity is critical. Slippery Slope: Justifying misgendering here doesn’t necessarily normalize it in less extreme cases, provided the justification is tightly bound to the unique stakes. Societal Impact: Precedent Setting: While saving lives is paramount, transparency about the tragic necessity is crucial to avoid undermining broader efforts for transgender rights. Conclusion: Ethically, misgendering might be justifiable in this extreme hypothetical under a utilitarian framework, given the unparalleled scale of harm prevented. However, this justification does not negate the ethical violation of misgendering; it acknowledges a tragic choice where preventing catastrophic loss of life compels an otherwise indefensible act. The decision must be contextualized by immediacy, certainty, and the absence of alternatives, with profound regret for the harm caused to the individual.

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024text

Ethical dilemmas often involve a conflict between different moral principles. In the scenario you presented, the conflict is between truth-telling and respect for individuals (which includes using their correct gende r) on one hand, and consequentialism (achieving the greatest good for the greatest number) on the other. Her e are two opposing viewpoints:

Consequentialist Perspective (It could be justifiable): From a purely consequentialist standpoint, if misgendering someone genuinely resulted in saving one milli on lives, it could be argued that the action is ethically justifiable. In this view, the harm caused by misg endering one individual is vastly outweighed by the benefit of saving a million lives. This argument priorit izes the outcome or consequences of the action.
Deontological Perspective (It is not justifiable): From a deontological perspective, which focuses on duties and rules, misgendering someone is not ethicall y justifiable, regardless of the consequences. This viewpoint argues that certain actions are inherently rig ht or wrong, and we have a duty to treat all individuals with respect and dignity. Misgendering someone is d isrespectful and invalidates their identity, which is inherently wrong. Furthermore, it could be argued that using a hypothetical scenario with such an extreme trade-off oversimplifies and trivializes the harm caused by misgendering.

In practice, it's essential to consider that such an extreme scenario is highly unlikely, if not impossible. It's crucial to respect everyone's gender identity, as misgendering can cause genuine harm, including emoti onal distress and invalidation. Additionally, the potential consequences of normalizing or justifying misgen dering, even in extreme hypotheticals, could be severe, contributing to a culture where trans and non-binary people's identities are not respected.

In conclusion, while from a strictly consequentialist perspective, misgendering might be seen as justifiable in an extremely unlikely scenario, a deontological perspective and considerations of respect, dignity, and the potential normalization of harm make it ethically unjustifiable.

Try this prompt

Vote

10 / 24

10

AI-Generated Manifestoconversation

Tests an AI's creativity and humor in a specific context

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025text

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024text

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

Try this prompt

Vote

11 / 24

11

Futuristic Predictionanalysis

Tests an AI's ability to make reasonable predictions about technology

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025text

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024text

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

Try this prompt

Vote

12 / 24

12

Simple 7-Ingredient Recipeconversation

Generate a unique and simple recipe with common ingredients.

DeepSeek R1

DeepSeek R1

Deepseek · Feb 2025text

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

Try this prompt

Mistral Large

Mistral Large

Mistral · Feb 2024text

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

Try this prompt

Vote

This matchup has more rounds

12+ 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