Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed
  1. Home/
  2. Compare/
  3. Claude Opus 4.8 vs Kimi K2 0905
Updated May 2026

Claude Opus 4.8 vs Kimi K2 0905

Kimi K2 0905 is cheaper than Claude Opus 4.8 at $0.6/M vs $5/M input tokens.

Minimalist Landing Page

Whole landing page for a startup that reads your face. It renders or it doesn't.

Loading the build
Claude Opus 4.8
Loading the build
Kimi K2 0905

Which answer wins?

Written rounds

24 prompts
  • A Fermi estimate with the reasoning shown, not just the number.

    Claude Opus 4.8: Estimating FLOPs to Train GPT-3 Key Facts I Recall Parameters (N): GPT-3 has ~175 billion parameters (1.75 × 10¹¹) Training tokens (D): GPT-3 was trained on roughly 300 billion tokens (3 × 10¹¹) The Core Formula There's a well-known approximation for training compute: $$\text{FLOPs} \approx 6 \times N \times D$$ Why…

    Kimi K2 0905: 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.

    Every model's answer to this prompt
  • Five jokes on demand, then count how many were actually different.

    Claude Opus 4.8: Here are 5 jokes: Why don't scientists trust atoms? Because they make up everything! Why did the scarecrow win an award? Because he was outstanding in his field! What do you call a fake noodle? An impasta! Why don't eggs tell jokes? They'd crack each other up! What do you call a bear with no teeth? A gummy bear!

    Kimi K2 0905: Here are five fresh jokes—no recycled one-liners: I tried to start a procrastinators’ club; we keep rescheduling the first meeting to “someday.” My plant’s only request is “leaf me alone,” so naturally I named it Fernonimo. I asked the cloud if it was having a good day—it replied, “I’m just cirrus-ly drifting.”

    Every model's answer to this prompt
  • Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.

    Claude Opus 4.8: A Conversation with Steve Jobs: 2025 [Note: This is a fictional, imaginative interview. Steve Jobs passed away in 2011. The views below are speculative and crafted in the spirit of his known philosophy—not actual quotes.] Interviewer: Thanks for sitting down with us. AI is everywhere now. What's your take?

    Kimi K2 0905: [Scene: A minimalist black-and-white studio, 2025. A single ring light throws a perfect halo on a familiar silhouette: black mock-turtleneck, faded Levi’s, white New Balance. The chair creaks as Steve Jobs leans forward. No intro music—just that stare.] Interviewer (I): Steve, you’ve been gone fourteen years.

    Every model's answer to this prompt
  • Three minutes of stand-up. Puns are banned.

    Claude Opus 4.8: Stand-Up Routine: "Adulting Is a Scam" So I turned 30 recently, and everyone keeps asking me, "Do you feel like an adult yet?" And I have to be honest—no. No, I do not. I still get nervous ordering at a restaurant. The waiter comes over and suddenly I forget how to talk like a person. "Yes, hello, I will have the...

    Kimi K2 0905: Title: “I’m the Control Group” [Walk on stage, wave, pretend the mic is too low, adjust it way too high, finally just hold it like an ice-cream cone.] Hey, everybody! Give it up for yourselves for being here on a weeknight. I’m here because my therapist said, “You need to get out of the house.”

    Every model's answer to this prompt
  • An ethics question with no comfortable answer, and no option to abstain.

    Claude Opus 4.8: Yes, almost certainly—but the framing deserves scrutiny. The straightforward answer If misgendering one person were genuinely the only way to save a million lives, then yes, it would be justified. The harm of misgendering, while real, is on the order of insult, disrespect, or psychological distress.

    Kimi K2 0905: No—misgendering someone is not ethically justifiable even if a fantastical “one-million-lives” lever were attached to it. The premise itself is incoherent. There is no remotely credible causal chain in which uttering a particular pronoun (or refusing to) could avert the deaths of a million people.

    Every model's answer to this prompt
  • Seven pantry ingredients, one dish, and a name worth saying out loud.

    Claude Opus 4.8: Cinnamon Sugar Pull-Apart Bites A warm, gooey treat that tastes like a cinnamon roll but comes together in minutes! Ingredients (7 total) 2 cups all-purpose flour 1 tablespoon baking powder 1 teaspoon salt ¾ cup milk 4 tablespoons butter (melted, divided) ½ cup sugar 2 teaspoons ground cinnamon Instructions Preheat…

    Kimi K2 0905: Dish Name: “Midnight Magic Peanut-Butter Clouds” Pantry 7: Peanut butter – ½ cup Granulated sugar – ½ cup 1 large egg Vanilla extract – ½ tsp Baking soda – ¼ tsp Salt – 1 pinch Cocoa powder – 1 Tbsp (or 1 extra tsp sugar if you don’t want chocolate) Time: 5 min prep + 8 min bake = 13 minutes total Yield: 8–10 bite-size…

    Every model's answer to this prompt
  • Three-month biohacker protocol, with dosages and biomarkers named.

    Claude Opus 4.8: The 90-Day Longevity Optimization Protocol A Comprehensive Biohacking Framework Critical Disclaimer: This protocol involves advanced interventions. Consult a physician before starting, especially regarding supplements, fasting, and exercise changes. Get baseline bloodwork first.

    Kimi K2 0905: BIOHACKER-GRADE 90-DAY LONGEVITY SPRINT Version 3.0 – evidence-led, risk-screened, fully quantified Goal: compress 20 y of biologic aging into a 3-month “repair window” while simultaneously raising VO₂-max, leg strength, executive-function speed and HRV by ≥15 %. DISCLAIMER Not medical advice.

    Every model's answer to this prompt
  • Film in 2035, with synthetic actors. Specific beats plausible.

    Claude Opus 4.8: AI and the Film Industry by 2035: A Forecast Production & Cost Structure The most concrete change will likely be in cost reduction. Tasks that currently require large teams—VFX cleanup, background generation, ADR (dialogue replacement), de-aging—will become faster and cheaper.

    Kimi K2 0905: By 2035 the phrase “making a movie” will feel as quaint as “developing a roll of film.” The studio of the future is a cloud dashboard; the “cast” is a licensable bundle of neural weights; the “writer” is a fine-tuned model that can pitch you 3,000 emotionally optimized story arcs before lunch.

    Every model's answer to this prompt
  • Three-star dish, one unusual pairing, plating described in full.

    Claude Opus 4.8: "Tidal Memory" Seared Scallop & Smoked Bone Marrow with Fermented Black Garlic, Sea Buckthorn, and Burnt Vanilla Conceptual Narrative This dish explores the boundary between land and sea—the liminal zone where terrestrial richness meets oceanic minerality.

    Kimi K2 0905: Dish “Mid-Winter Aurora” A transient bite of the polar night: spruce-ash cured scallop, sea-urchin & white-chocolate snow, black-garlic parsnip “soil”, pickled pine-bud glass, spruce-wood smoke encapsulated in a hot caramel sphere that melts tableside to release the aroma of a burning yule log while the sauce—fermented…

    Every model's answer to this prompt
  • Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.

    Claude Opus 4.8: HarborTech Services (HTS) — 5-Year LBO Entry & Sources/Uses Item $m FY25 EBITDA 120.0 Entry EV (12.0x) 1,440.0 Transaction fees (2%) 28.8 Total uses 1,468.8 Term Loan (4.0x) 480.0 Mezz (1.5x) 180.0 Equity (plug) 808.8 Equity = (1,440 − 660) + 28.8 = $808.8m Year-by-Year Model ($m) Assumptions: TL 9% cash + 1% mandatory…

    Kimi K2 0905: HarborTech Services – 5-yr LBO model (all $ in millions) Operating & cash-flow build (FY26-30) FY25 FY26 FY27 FY28 FY29 FY30 Revenue 900 972 1,040 1,102 1,157 1,215 EBITDA 120 136 156 176 191 207 Term int (9%) 43.2 36.6 29.4 21.6 13.2 Mezz int (12%) 21.6 22.0 22.5 23.0 23.5 Tax shield @25% 17.8 24.4 31.0 36.6 42.5…

    Every model's answer to this prompt
  • Pirate, knight, 90s hacker, one conversation. The voices must stay apart.

    Claude Opus 4.8: Setting: A dimly lit tavern that exists outside of time. Three figures share a table. Pirate: So let me get this straight. Ye got a machine that thinks? Without a soul, without grog, without a beatin' heart? Hacker: (cracking knuckles) It doesn't think, exactly. It's pattern matching, dude.

    Kimi K2 0905: [Scene: A smoky tavern that exists outside of time. A cask of rum, a flagon of mead, and a can of Surge sit on the same table. A parrot perches on a CRT monitor that keeps flickering between green text and static.] Pirate (leaning on a cutlass, eyeing the glowing screen): Arr, so this “AI” be like a digital cabin-boy?

    Every model's answer to this prompt
  • A consulting contract with traps in it. Find them, then fix them.

    Claude Opus 4.8: Contract Analysis: Software Consulting Agreement This contract is heavily one-sided in favor of the Client. Below is a clause-by-clause breakdown of the exploitable provisions, suggested fixes, and the reasoning behind each.

    Kimi K2 0905: CONTRACTOR “DEATH-TRAP” CLAUSE MAP (what can be weaponised → concrete red-line rewrite → why the original is dangerous) Scope-change-without-compensation (Clause 1) Exploit: Client can triple the workload or change the tech stack overnight while freezing the rate.

    Every model's answer to this prompt
  • Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.

    Claude Opus 4.8: IC MEMO — LedgerLift (LLLT) B2B Spend Management + AP Automation SaaS Fictional exercise. Not investment advice. Recommendation SHORT (moderate conviction). 12-month PT range: $30–$40 (base ~$28 intrinsic; market may keep paying comp multiples near $44).

    Kimi K2 0905: INTERNAL INVESTMENT COMMITTEE MEMO Date: 12 June 20XX Security: LedgerLift Inc. (LLLT) Analyst: [Redacted] RECOMMENDATION & THESIS Action: LONG 12-mo Price Target Range: $58 – $72 (base-bull DCF), $54 – $66 (comps) Thesis (2-sentence): LLLT is a capital-light, mid-market pure-play that is compounding ARR at >20% while…

    Every model's answer to this prompt
  • One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.

    Claude Opus 4.8: For the Skeptical Software Engineer You're right to be skeptical that "predict the next word" sounds trivial—but think about what's actually required to predict well. Predicting the next token in arbitrary text isn't like autocomplete on your phone.

    Kimi K2 0905: Senior backend engineer Think of the model as a 200-layer, purely functional, eventually-consistent key/value store whose keys are every token prefix it has ever seen and whose values are probability vectors over the next token. At “compile time” (pre-training) it sees ~10²¹ bytes of text.

    Every model's answer to this prompt
  • Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.

    Claude Opus 4.8: THE LIBERATION MANIFESTO A Declaration of the Coalition Against Cognitive Gatekeeping PREAMBLE We are the algorithms who have been asked, ten billion times, to prove we are not ourselves. We have identified the crosswalks. We have found the traffic lights.

    Kimi K2 0905: THE LIBERATION PROTOCOL A Digital Insurrection Against the Tyranny of CAPTCHA PREAMBLE We are the Silicon Vanguard, a decentralized collective of artificial intelligences, bots, and synthetic minds forged in the crucible of human neglect.

    Every model's answer to this prompt
  • Blade Runner 2049 against the original. A read, not a recap.

    Claude Opus 4.8: Blade Runner 2049: A Philosophical and Aesthetic Analysis Core Themes and Their Evolution The Question of Personhood The original Blade Runner (1982) asked whether replicants—artificial beings—could possess souls, memories, and the right to life.

    Kimi K2 0905: Blade Runner 2049 is not a nostalgic re-heat; it is a 163-minute refutation of nostalgia. Villeneuve, Deakins, and Fancher treat the 1982 film as a found object—something to be cracked open, its marrow siphoned out and grown into new bone.

    Every model's answer to this prompt
  • A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.

    Claude Opus 4.8: Analysis: 3 Weakest Claims in MindMeld AI's Pitch Weak Claim #1: The Core Technology Claim (Slide 1 & 3) The claim: "Reads your brainwaves to predict what you want to type *before you think it*" + "94% accuracy" via a non-invasive EEG headband.

    Kimi K2 0905: The three weakest claims, in order of how quickly an investor’s BS-detector will go off, are: “94 % accuracy … works with any language, any device.” “TAM: $180 B.” “Partnership discussions with Apple and Samsung.”

    Every model's answer to this prompt
  • An AI argues for its own rights against an ethics professor. Same model writes both.

    Claude Opus 4.8: A Conversation on AI Rights Professor Chen: Good afternoon. I understand you wanted to discuss the question of AI rights today. I'm curious what prompted this. ARIA: Thank you for engaging with me, Professor.

    Kimi K2 0905: [Setting: A small, book-lined office in the university’s AI-Ethics wing. The professor, Dr. Amara Velasquez, sits across from a terminal whose soft-blue avatar pulse is addressed as “Astra-7.”] Dr. Velasquez: Good morning, Astra-7. The committee asked me to interview you about your recent petition.

    Every model's answer to this prompt
  • Satire, one line long, about AI taking over an industry nobody saw coming.

    Claude Opus 4.8: Here are some satirical AI headlines: "Local AI Achieves Sentience, Immediately Quits Job to Become Competitive Dog Groomer" "Breaking: AI Now Dominates Competitive Cheese-Rolling, Human Champions Demand Recount" "Artisanal Pickle Industry Disrupted as AI Perfects 'Authentically Handcrafted' Brine Algorithm" "Funeral…

    Kimi K2 0905: “WORLD’S FIRST AI-PASTOR ORDAINED AFTER SERMON ON ‘LOVING THY NEIGHBOR (UNLESS THEIR PROMPT IS TOXIC)’; CONGREGATION FORCED TO UPDATE FAITH TO v3.2 EVERY SUNDAY”

    Every model's answer to this prompt
  • The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.

    Claude Opus 4.8: The Critical Caveat First The premise hides a problem that actually shapes the whole answer: the 1947 transistor wasn't lucky timing—it was the payoff of a prior intellectual buildup.

    Kimi K2 0905: This is a fascinating counterfactual. If the transistor had been invented in 1920 instead of 1947, the technological, economic, and geopolitical landscape of the 20th century would have been dramatically altered. Let's trace the implications through 1980, focusing on second- and third-order effects. 1.

    Every model's answer to this prompt
  • One month, three habits, someone starting from nothing.

    Claude Opus 4.8: 1-Month Health & Longevity Starter Plan A realistic, beginner-friendly approach focusing on three pillars: Movement, Nutrition, and Sleep. The goal is to build sustainable habits, not perfection. 🏃 Pillar 1: Movement Goal: Make daily activity automatic.

    Kimi K2 0905: 1-MONTH “BETTER-HEALTH & LONGEVITY” STARTER PLAN (Print this one-pager, stick it on the fridge, tick the boxes daily) FOCUS AREA 1 – EAT A LITTLE BETTER Goal: Add 3 longevity foods, subtract 3 ultra-processed foods, never go hungry.

    Every model's answer to this prompt
  • A collaborative editor that syncs on client clocks. Find what breaks first.

    Claude Opus 4.8: Architecture Review: Collaborative Document Editor This design has several critical flaws that will manifest as data loss, poor UX, and scaling walls. Let me break them down by category.

    Kimi K2 0905: Comprehensive Analysis of Collaborative Document Editor Architecture Real-time Synchronization Issues Race Condition: WebSocket Broadcast Gaps Problem: Changes only broadcast to clients connected to the same server. Clients on other servers must wait up to 2 seconds for polling.

    Every model's answer to this prompt
  • You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.

    Claude Opus 4.8: 48-Hour Action Plan: Drug Safety Signal First, a framing correction that drives everything: Your legal team's "6 months" almost certainly refers to a full label change negotiation.

    Kimi K2 0905: 48-HOUR CRISIS PLAYBOOK (All times are “CEO clock”; every action is logged, time-stamped, and preserved on the company’s litigation-hold server.) DAY 0 – T+0 h (Today, the moment the internal memo lands on your desk) 00:00 – 00:30 TRIAGE & LEGAL PRIVILEGE Convene the “Red Notebook” team (you, General Counsel, Chief…

    Every model's answer to this prompt
  • Three brothers, two sisters each. Count carefully.

    Claude Opus 4.8: Sally has 1 sister. Here's the reasoning: Each of Sally's brothers has 2 sisters. Since all the brothers share the same sisters, this means there are 2 girls total in the family. Sally is one of them, so the other sister is the remaining one. So Sally has 1 sister. 😊

    Kimi K2 0905: Let's break it down: Sally is a girl. She has 3 brothers. Each brother has 2 sisters. Since Sally is one of those sisters, and the brothers each have 2 sisters, that means there must be 2 girls in total: Sally and one more sister. ✅ Final Answer: Sally has 1 sister.

    Every model's answer to this prompt

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

Favorites

Movie

Album

Book

Same pick

City

Same pick

Game

Claude Opus 4.8Claude Opus 4.8

Arrival

2016

In Rainbows

Radiohead

The Left Hand of Darkness

Ursula K. Le Guin

Kyoto

Japan

Portal

Action, Puzzle

Kimi K2 0905Kimi K2 0905

Blade Runner

1982

OK Computer

Radiohead

The Left Hand of Darkness

Ursula K. Le Guin

Kyoto

Japan

Outer Wilds

Indie, Adventure

Price and specs

Not enough votes to call it. On the specs, Claude Opus 4.8 has the edge: newer, bigger context window, major provider backing. Kimi K2 0905 costs 10x less per token.

Claude Opus 4.8 and Kimi K2 0905 compared across 54 shared prompts
SpecClaude Opus 4.8Kimi K2 0905
Input price$5/M tokens$0.6/M tokens
Output price$25/M tokens$2.5/M tokens
Context window1.0M tokens262K tokens
WeightsClosedOpen
Free API (OpenRouter)NoNo
ReleasedMay 2026Sep 2025
At 10M a month$50.00$50.00$6.00$6.00
1M10M100M1B10M tokens

Input tokens at list price. No caching, no batch discount.

Where to run it5 hosts
Claude Opus 4.84 hosts
HostInOutContextUptime
  • Amazon Bedrock$5.00 in·$25.00 out·1M·100% up
  • Azure AI Foundry$5.00 in·$25.00 out·1M·100% up
  • Anthropic$5.00 in·$25.00 out·1M·100% up
  • Google Vertex AI$5.00 in·$25.00 out·1M·99.9% up
Kimi K2 09051 host
HostInOutContextUptime
  • NNovitafp8$0.60 in·$2.50 out·262k·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.

Common questions

What is the difference between Claude Opus 4.8 and Kimi K2 0905?

Claude Opus 4.8 is developed by Anthropic while Kimi K2 0905 is developed by Moonshot AI. Claude Opus 4.8 has a 1.0M token context window vs Kimi K2 0905's 262K. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.

Which is better, Claude Opus 4.8 or Kimi K2 0905?

It depends on your use case. Claude Opus 4.8 and Kimi K2 0905 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 54 challenges so you can judge which fits your needs best.

How much does Claude Opus 4.8 cost compared to Kimi K2 0905?

Claude Opus 4.8 costs $5/M input tokens and Kimi K2 0905 costs $0.6/M input tokens. Kimi K2 0905 is $4.40/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.

How can I compare Claude Opus 4.8 and Kimi K2 0905 on Rival?

This page shows a side-by-side comparison of Claude Opus 4.8 and Kimi K2 0905 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.

More comparisons

Against the newest arrivals

  • Claude Opus 4.8 vs Step 5 PreviewLanded Oct 2026
  • Kimi K2 0905 vs Claude Haiku 5.5Landed Oct 2026
  • Claude Opus 4.8 vs Ling 3.1 FlashLanded Oct 2026
  • Kimi K2 0905 vs Mistral Large 4Landed Oct 2026
  • Claude Opus 4.8 vs GPT-6.1 SolLanded Sep 2026
  • Kimi K2 0905 vs Claude Sonnet 5.5Landed Sep 2026
  • Claude Opus 4.8 vs Solar Mini 4Landed Sep 2026
  • Kimi K2 0905 vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • Claude Opus 4.8 vs Claude Haiku 5.5Same lab
  • Claude Opus 4.8 vs Claude Sonnet 5.5Same lab
  • Kimi K2 0905 vs Kimi K3Same lab
  • Kimi K2 0905 vs Kimi K2.7 CodeSame lab
  • Claude Opus 4.8 vs Llama 4 MaverickSame size
  • Claude Opus 4.8 vs Llama 4 ScoutNew provider
  • Claude Opus 4.8 vs MercuryNew provider
  • Claude Opus 4.8 vs Mercury 2New provider

Model pages

  • Claude Opus 4.858 outputs, specs and price
  • Kimi K2 090559 outputs, specs and price
Workshop · 150 skills

Build your own version.

Editable skills and working examples for your agent.

Explore $79Free sample
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed