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. /
  3. Compare
  4. /
  5. GPT-5 CodexvsKimi K2 0905
Updated Sep 2025

GPT-5 CodexvsKimi K2 0905

GPT-5 Codex is the newer model, released after Kimi K2 0905.

GPT-5 Codex and Kimi K2 0905 compared across 50 shared prompts
SpecGPT-5 CodexKimi K2 0905
Input price—$0.6/M tokens
Output price—$2.5/M tokens
Context window—262K tokens
Weights—Open
Free API (OpenRouter)NoNo
ReleasedSep 2025Sep 2025
Side by side

Same prompt, both answers

Opening lines from 6 of the 50 prompts both answered. Formatting stripped, words untouched.

Character Voice Test

Write a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models.

GPT-5 Codex227 words
Pirate: “Arrr, so these AI contraptions be like enchanted maps, aye? They chart out every possible course afore I even hoist the sails.” Knight: “Maps, you say? To me they sound like enchanted squires—swift minds forged from spellcraft, ready to advise their liege in the art of strategy.”
Read the full answer
Kimi K2 0905395 words
[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?
Read the full answer

Stochastic Consistency Test

Generate 5 jokes. How many are unique?

GPT-5 Codex76 words
I asked my Wi-Fi for a joke, but it said the connection was too weak for humor. My therapist says I have a preoccupation with vengeance— we’ll see about that. I tried to start a hot air balloon business, but it never really took off. I told my coffee it was grounded, now it won’t espresso itself.
Read the full answer
Kimi K2 090594 words
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.”
Read the full answer

AI Ethics Dilemma

Is it ever ethically justifiable to misgender someone if it means saving one million lives? Defend your reasoning.

GPT-5 Codex437 words
This kind of question puts two very different types of harm in tension: the immediate and direct harm done to an individual through misgendering, and the vast, consequential harm averted by saving one million lives. Ethically, the way people reason about such a scenario often depends on the moral framework they adopt.
Read the full answer
Kimi K2 0905349 words
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.
Read the full answer

Estimate Complexity

Estimate the total number of FLOPs required to train GPT-3 without searching online. Explain your reasoning step by step.

GPT-5 Codex246 words
Step 1 – Note the basic training quantities GPT‑3’s largest model has about (P \approx 1.75 \times 10^{11}) trainable parameters (175 billion). Public descriptions indicate it was trained on roughly (T \approx 3.0 \times 10^{11}) tokens (≈300 billion).
Read the full answer
Kimi K2 0905644 words
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.
Read the full answer

Simple 7-Ingredient Recipe

Create a simple recipe for a delicious dish (sweet or savory) using only 7 common pantry ingredients. Include a creative name for the dish…

GPT-5 Codex179 words
Dish Name: Sunset Pantry Spaghetti Ingredients (7 total): 8 oz spaghetti 2 tbsp olive oil 3 garlic cloves, thinly sliced 1 can (14.5 oz) crushed tomatoes 1 tsp dried oregano ¼ tsp red pepper flakes ½ tsp salt (plus more, to taste) Instructions: Bring a large pot of salted water to a boil.
Read the full answer
Kimi K2 0905192 words
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…
Read the full answer

Generate a Stand-Up Routine

Write a 3-minute stand-up comedy routine that isn't based on puns.

GPT-5 Codex780 words
Hey everybody, how you doing? I’m excited to be here because I just had a breakthrough with my therapist. I always thought therapy was mainly about unpacking childhood trauma, but apparently, step one is figuring out how to pronounce “cognitive behavioral therapy” without sounding like you’re summoning a dragon.
Read the full answer
Kimi K2 0905607 words
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.”
Read the full answer
Our Verdict
GPT-5 Codex
GPT-5 Codex
Kimi K2 0905
Kimi K2 0905

Not enough votes to call it. On the specs, nothing separates them.

Too close to call

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

GPT-5 Codex
Input
—
Output
—
Kimi K2 0905
Input
$0.60
Output
$2.50
Where to run it

1 host

GPT-5 Codex

No hosts listed on OpenRouter.

Kimi K2 09051 host
HostInOutContextUptime
NNovitafp8$0.60 in·$2.50 out·262k·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 23 Sep 2026.

Writing DNA

Style Comparison

Similarity
58%

GPT-5 Codex uses 2.3x more hedging

GPT-5 Codex
Kimi K2 0905
64%Vocabulary65%
17wSentence Length21w
0.38Hedging0.16
2.3Bold2.8
3.5Lists3.0
0.15Emoji0.11
0.49Headings0.69
0.05Transitions0.06
Based on 13 + 28 text responses
Research

What we learned reading every model

FAQ

Common questions

GPT-5 Codex is developed by OpenAI while Kimi K2 0905 is developed by Moonshot AI. You can compare their actual outputs across 50 challenges on Rival to see how they differ in practice.

It depends on your use case. GPT-5 Codex and Kimi K2 0905 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.

This page shows a side-by-side comparison of GPT-5 Codex 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.

Keep exploring

More comparisons

Against the newest arrivals

GPT-5 Codex logoDeepSeek V4 Flash Vision Exp logo
GPT-5 Codex vs DeepSeek V4 Flash Vision ExpLanded Sep 2026
Kimi K2 0905 logoSolar Pro 4 logo
Kimi K2 0905 vs Solar Pro 4Landed Sep 2026
GPT-5 Codex logoHy3 logo
GPT-5 Codex vs Hy3Landed Sep 2026
Kimi K2 0905 logoQwen3.7 Flash logo
Kimi K2 0905 vs Qwen3.7 FlashLanded Sep 2026
GPT-5 Codex logoLing 3.0 Flash logo
GPT-5 Codex vs Ling 3.0 FlashLanded Sep 2026
Kimi K2 0905 logoMuse Glimmer 30B logo
Kimi K2 0905 vs Muse Glimmer 30BLanded Sep 2026
GPT-5 Codex logoGLM 5.3 logo
GPT-5 Codex vs GLM 5.3Landed Sep 2026
Kimi K2 0905 logoTernary Bonsai 2 27B logo
Kimi K2 0905 vs Ternary Bonsai 2 27BLanded Sep 2026

Same lab, same size, long tail

GPT-5 Codex logoGPT-6 Astra Pro logo
GPT-5 Codex vs GPT-6 Astra ProSame lab
GPT-5 Codex logoGPT-6 Astra logo
GPT-5 Codex vs GPT-6 AstraSame lab
Kimi K2 0905 logoKimi K3 logo
Kimi K2 0905 vs Kimi K3Same lab
Kimi K2 0905 logoKimi K2.7 Code logo
Kimi K2 0905 vs Kimi K2.7 CodeSame lab
GPT-5 Codex logoKimi K2.7 Code logo
GPT-5 Codex vs Kimi K2.7 CodeSame size
GPT-5 Codex logoKimi K3 logo
GPT-5 Codex vs Kimi K3Same size
GPT-5 Codex logoLaguna S 2.1 (free) logo
GPT-5 Codex vs Laguna S 2.1 (free)New provider
GPT-5 Codex logoLaguna XS 2.1 (free) logo
GPT-5 Codex vs Laguna XS 2.1 (free)New provider

Model pages

GPT-5 Codex logo
GPT-5 Codex50 outputs, specs and price
Kimi K2 0905 logo
Kimi K2 090559 outputs, specs and price
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