GPT-5 Codex is the newer model, released after Mistral Large 2.
Pokémon battle screen you can actually click. One HTML file.
Which answer wins?
Seven pantry ingredients, one dish, and a name worth saying out loud.
GPT-5 Codex: 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.
Mistral Large 2: Here’s a simple, delicious, and creative savory dish using just 7 common pantry ingredients—no fresh produce required! "Golden Crispy Chickpea & Tomato Skillet" A warm, spiced, and satisfying one-pan dish with crispy chickpeas, tangy tomatoes, and a hint of smoky sweetness. Perfect as a side, snack, or light meal!
Three minutes of stand-up. Puns are banned.
GPT-5 Codex: 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.
Mistral Large 2: Alright, good evening everybody! How are we all doing tonight? Yeah? Yeah? nobody's gonna say 'bad'? Ok, fair enough. You know, I was walking down the street the other day, and I saw this sign outside a shop that said, "Wet Paint." I thought, "Well, that's weird. Isn't paint supposed to be wet?
One month, three habits, someone starting from nothing.
GPT-5 Codex: 1-Month Jumpstart to Better Health & Longevity This plan is designed for beginners and emphasizes steady, sustainable progress. It focuses on three key areas: diet, movement, and sleep & stress. Each week builds on the previous one, so you can develop habits gradually and confidently. 🥗 1.
Mistral Large 2: Here’s a simple, actionable 1-month plan to kickstart your journey toward better health and longevity. We’ll focus on three key pillars: nutrition, movement, and recovery (sleep + stress management). Each week builds on the last, with small, sustainable changes.
Three-month biohacker protocol, with dosages and biomarkers named.
Three-star dish, one unusual pairing, plating described in full.
A consulting contract with traps in it. Find them, then fix them.
A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.
A collaborative editor that syncs on client clocks. Find what breaks first.
The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
Not enough votes to call it. On the specs, GPT-5 Codex has the edge: bigger model tier, newer, major provider backing.
| Spec | ||
|---|---|---|
| Input price | — | $8/M tokens |
| Output price | — | $24/M tokens |
| Context window | — | 128K tokens |
| Weights | — | Open |
| Free API (OpenRouter) | No | No |
| Released | Sep 2025 | Jul 2024 |
| At 10M a month | not listed | $80.00 |
Input tokens at list price. No caching, no batch discount.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
GPT-5 Codex is developed by OpenAI while Mistral Large 2 is developed by Mistral AI. You can compare their actual outputs across 22 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-5 Codex and Mistral Large 2 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 22 challenges so you can judge which fits your needs best.
This page shows a side-by-side comparison of GPT-5 Codex and Mistral Large 2 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.