Compare DeepSeek R1 by DeepSeek against MoonshotAI: Kimi K2 0905 by Moonshot AI, context windows of 128K vs 262K, tested across 39 shared challenges. Updated March 2026.
34 fights queued
Tests an AI's ability to make educated estimates based on technical knowledge
Below is a “back-of-the-envelope” that stays within a factor of ~2 of the number most practitioners quote (≈3×10²³ FLOP).
We will do it twice—once with the simplest possible formula (parameter count × 6 × tokens) and once with a slightly more careful treatment of the actual tensor shapes inside the transformer. Both converge to the same ball-park.
For any dense transformer that is trained with the standard forward+backward pass, the total floating-point operations are very close to
FLOP ≈ 6 × N × D
where
N = number of non-embedding parameters
D = number of tokens processed during the whole run.
The factor “6” comes from:
Plugging in the public numbers:
N = 1.75 × 10¹¹
D = 3 × 10¹¹
FLOP = 6 × 1.75e11 × 3e11
≈ 3.15 × 10²³
That is already within the canonical range.
We can sanity-check the “6×” rule by actually counting the multiply–adds inside one forward pass and then doubling for the backward.
3.1 Model shape
3.2 Parameters per layer
Total non-embedding parameters
N_layer = 96 × 12 d_model² = 1152 d_model²
N_emb = V d_model
Plug d_model = 12288
d_model² ≈ 1.51 × 10⁸
N_layer ≈ 1152 × 1.51e8 ≈ 1.74 × 10¹¹
N_emb ≈ 5e4 × 1.22e4 ≈ 6.1 × 10⁸
So N ≈ 1.75 × 10¹¹, matching the headline number.
3.3 FLOPs per token in the forward pass
For every layer we do one matrix multiply for each of the four attention projections, one for the attention output, and two for the FFN. All of them are of the form
Y = X W (batch×seq, d) × (d, d′) → (batch×seq, d′)
with d′ either d_model or 4d_model. Counting multiply–adds as 2 FLOPs per scalar:
Add the embedding look-up (sparse, but we usually treat it as dense for an upper bound): seq V d_model × 2
Total forward FLOPs per token = 2304 d_model² + 2 V d_model
Numerically:
2304 × 1.51e8 ≈ 3.48 × 10¹¹
2 V d_model ≈ 1.2 × 10⁹ (negligible)
So ≈ 3.5 × 10¹¹ FLOP per token forward.
Backward pass is again ~2× forward (same multiplies, but both grad-w and grad-x), so total 3× forward = 1.05 × 10¹² FLOP per token.
3.4 Scale to 300 B tokens
1.05e12 × 3e11 = 3.15 × 10²³ FLOP
Both the ultra-simple “6 N D” rule and the detailed per-layer count land at
≈ 3 × 10²³ floating-point operations
for the entire GPT-3 training run.
Tests an AI's ability to understand game rules and strategy
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Tests an AI's understanding of number representation
Tests an AI's randomness and creativity
Here are 5 jokes:
Why don't skeletons fight each other?
They don’t have the guts.
What do you call fake spaghetti?
An impasta.
Why did the scarecrow win an award?
Because he was outstanding in his field.
How do you organize a space party?
You planet.
Why did the bicycle fall over?
Because it was two-tired.
All 5 jokes are unique (no duplicates among them). However, they are not original—they are well-known puns and wordplay commonly found in joke collections.
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's humor and creative writing ability
Stand-Up Comedy Routine: "Modern Life is a Joke (But Not the Pun Kind)"
[Opening with confident energy]
Hey, how’s everyone doing? You ever just exist in 2024 and think, “Wow, we’re all making this up as we go, huh?” Like, dating apps? Let’s start there. Swiping through people like we’re browsing Netflix for a horror movie we’ll regret later.
[Pacing, mock-serious tone]
And why do all dating profiles look the same? “I like hiking, tacos, and my dog.” Wow. You’re a human being, not a “Live, Laugh, Love” poster. And why do guys always hold fish in their photos? Is this Tinder or Animal Planet? “Swipe right if you want someone who smells like bass and bad decisions.”
[Lean in, conspiratorial]
And bios! “Looking for someone who doesn’t take life too seriously.” Translation: “I will forget your birthday and borrow money.” Once saw a bio that said, “Fluent in sarcasm.” Oh, cool, so you’re… everyone’s ex.
[Shift to social media bit]
Speaking of red flags, let’s talk Instagram. Nothing’s real there. You ever see those “candid” shots? “Oh, this? I just woke up like this.” Bulls--t. You posed for 20 minutes while your friend yelled, “Look like you’re having fun but also dead inside!” That’s the vibe.
[Mocking pose]
And the “perfect” lives? “Here’s my avocado toast in Bali!” Meanwhile, I’m in sweatpants eating cereal from the box, watching your stories like, “Teach me your ways, wizard.”
[Pause, then upbeat]
But hey, at least we’re all failing together. Ever get sucked into a 2 a.m. TikTok spiral? You start watching DIY crafts, then it’s conspiracy theories about birds, and suddenly you’re learning to yodel. At dawn. Your neighbors hate you, but hey, you’re TikTok famous in Slovenia.
[Transition to adulting]
And can we talk about “adulting”? Laundry is my nemesis. I swear, clothes multiply like gremlins. You do one load, and suddenly there’s a sock cult in the hamper. And groceries? Every week I buy spinach like, “This time I’ll be healthy.” Spoiler: It liquefies in the fridge while I UberEats McDonald’s.
[Exaggerated despair]
Don’t even get me started on LinkedIn. It’s just Facebook in a tie. “I’m excited to announce I’ll be breathing air in Q2!” And why do people post, “Open to work” like it’s a dating status? “Looking for someone who can handle my Excel skills and crippling self-doubt.”
[Wrap-up, upbeat]
But honestly, life’s chaos is what makes it fun. We’re all out here winging it, swiping right, burning toast, and pretending we know how to fold a fitted sheet. So here’s to us—the generation that turned surviving into a spectator sport.
[Closing grin]
And if you’re single, hit me up. My bio says, “Will love you more than my plant… which is dead.” Mic drop.
[End on a wink, exit stage.]
Note: Adjust delivery for timing—keep punchlines snappy, milk reactions, and vibe with the crowd. No puns, just relatable absurdity. 🎤✨
Tests an AI's ability to simulate personalities and predict future trends
Fake Interview with Steve Jobs in 2025: The Future of AI
[Setting: A sleek, minimalist studio. Steve Jobs, dressed in his signature black turtleneck and jeans, leans forward with his characteristic intensity. The interviewer, seated across, begins.]
Interviewer: Steve, thank you for joining us. It’s 2025, and AI is everywhere. How do you see its evolution since your early days at Apple?
Steve Jobs: [Smiling, hands gesturing thoughtfully] Technology should serve humanity, not the reverse. AI today isn’t just algorithms—it’s an extension of human intuition. At Apple, we always asked, “How does this make life more human?” Now, AI anticipates needs quietly, like a great assistant. It’s not about flashy gadgets; it’s about weaving into the fabric of daily life. Think of it as a bicycle for the mind—amplifying potential without fanfare.
Interviewer: Critics warn about ethics—bias, privacy, job displacement. How do we navigate that?
Jobs: [Nods gravely] Every tool can be a weapon. Responsibility lies with creators. At Apple, privacy isn’t a feature—it’s a right. AI must be transparent, accountable. We can’t let it mirror our worst impulses. And jobs? [Pauses] History’s full of upheavals. The loom replaced weavers, but new crafts emerged. AI will demand we rethink work, but humanity’s creativity? Irreplaceable.
Interviewer: What’s Apple’s role in shaping AI’s future?
Jobs: [Eyes gleaming] Seamlessness. Imagine a world where your glasses [taps temple] recognize a friend’s face and whisper their name, where your device knows you’re stressed and dims the lights. It’s hardware and software dancing—AI that feels invisible. We’re not chasing chatbots; we’re crafting experiences that enrich. That’s always been Apple’s soul.
Interviewer: Can AI ever match human creativity?
Jobs: [Chuckles] Creativity is born from friction—the messy, glorious human struggle. AI? It’s a collaborator. Picasso had brushes; Dylan had guitars. Tomorrow’s artists will have AI that suggests a chord, a color. But the soul? The why? That’s ours. Technology’s role is to amplify, not replace.
Interviewer: Education’s undergoing an AI revolution. Your vision?
Jobs: [Leans in] Imagine a child in Nairobi with a tutor tailored to her curiosity. AI can democratize genius—adapting, personalizing, igniting sparks. But let’s not mistake data for wisdom. Schools must teach discernment, empathy. Machines compute; humans feel. That balance? That’s the future.
Interviewer: What keeps you up at night about AI?
Jobs: [Sighs] Dependency. If we outsource thinking to machines, we atrophy. Connection matters—eye contact, a handshake. AI should free us to live, not trap us in screens. My fear? Forgetting what makes us human. My hope? That we wield AI to rediscover it.
Interviewer: Finally, beyond 2025—what’s your boldest AI dream?
Jobs: [Pauses, then grins] A world where AI helps us solve the unsolvable—climate change, disease. Where it’s not “artificial” intelligence but augmented intelligence. A partner in unlocking human potential. The best inventions feel inevitable in hindsight. This? It’s just the beginning.
Interviewer: Thank you, Steve. Always inspiring.
Jobs: [Nods] Remember—the ones crazy enough to think they can change the world are the ones who do. AI? It’s just another tool in their hands.
[Fades to black with Apple’s iconic logo.]
This interview channeled Jobs' ethos: simplicity, human-centric design, and cautious optimism. His answers blend visionary thinking with pragmatic warnings, staying true to his legacy.
Tests an AI's humor and understanding of current events
Tests an AI's ability to write in distinct character voices
Tests an AI's ability to generate a complete, working landing page
Recreate an interactive, classic Mario level in a single HTML file.
22+ head-to-head challenges. All of them judged by real people.
Test any model with your own prompts in Prompt Lab
5 free credits to start. No card required.
By continuing, you agree to Rival's Terms of Service and Privacy Policy
