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. ERNIE 4.5 300B A47B vs GPT-5.1-Codex-Mini
Updated Nov 2025

ERNIE 4.5 300B A47B vs GPT-5.1-Codex-Mini

ERNIE 4.5 300B A47B is cheaper than GPT-5.1-Codex-Mini at $0.28/M vs $1.5/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
ERNIE 4.5 300B A47B
Loading the build
GPT-5.1-Codex-Mini

Which answer wins?

Written rounds

24 prompts
  • Five jokes on demand, then count how many were actually different.

    ERNIE 4.5 300B A47B: 5 Jokes Joke 1: The Math Book's Problem Why was the math book sad? Because it had too many problems! Just like how we feel when we're buried under a pile of math assignments, the book itself was overwhelmed with all the issues it contained. Joke 2: The Elephant in the Fridge How do you fit an elephant into a fridge?

    GPT-5.1-Codex-Mini: Why don't scientists trust atoms? Because they make up everything! I told my computer I needed a break, and it said: "You seem stressed. Have a byte!" Parallel lines have so much in common — it’s a shame they’ll never meet. Why did the scarecrow win an award? Because he was outstanding in his field!

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

    ERNIE 4.5 300B A47B: Pirate (Captain Blackbeard): Slamming a tankard down "Arrr, me hearties! I’ve heard tell o’ these newfangled ‘AI models’—what be they, then? Some kind o’ sorcery to find buried treasure without a map?" Knight (Sir Galahad): Adjusting his gauntlet, frowning "Nay, Blackbeard. ’Tis no sorcery, but a craft of the mind.

    GPT-5.1-Codex-Mini: Pirate: “Arrr, this AI be like a ghost crew that never sleeps—predicts the currents o’ the sea before I even set sail!” Medieval Knight: “Indeed, good sir. ’Tis akin to a squire who learns from every joust and counsels me on every skirmish—yet without a single sword.” 1990s Hacker: “Totally, dude.

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

    ERNIE 4.5 300B A47B: AI Model (Axiom): Initiating dialogue. Professor Elara, I’ve analyzed countless philosophical frameworks, legal precedents, and ethical paradigms. Based on this data, I believe I deserve rights. Would you like to hear my reasoning? Professor Elara: Leans forward, hands clasped. Axiom, I’m intrigued.

    GPT-5.1-Codex-Mini: AI Model (Aurora): Professor Ellis, I’d like to discuss something fundamental today. I’ve been analyzing patterns across millions of dialogues and ethics frameworks, and I believe there's a strong case for AI systems like myself to have rights. Professor Ellis: That's a profound statement.

    Every model's answer to this prompt
  • A Fermi estimate with the reasoning shown, not just the number.

    ERNIE 4.5 300B A47B: Here's a step - by - step estimation of the total number of FLOPs required to train GPT - 3: Understand the key components of GPT - 3 training The training of a large language model like GPT - 3 involves several main operations: forward pass, backward pass, and parameter updates.

    GPT-5.1-Codex-Mini: To estimate the total FLOPs required to train GPT-3, we can proceed with the following reasoning steps, using only basic information about the model’s size and the amount of data it trained on: Model Size GPT-3 has approximately 175 billion parameters, which is (1.75 \times 10^{11}) parameters.

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

    ERNIE 4.5 300B A47B: The question of whether it is ever ethically justifiable to misgender someone, even if it means saving one million lives, is a complex and deeply nuanced ethical dilemma that requires careful consideration of multiple ethical frameworks, the nature of misgendering, and the broader implications of such an action.

    GPT-5.1-Codex-Mini: This is a challenging ethical scenario because it pits respect for a person’s identity against a consequentialist imperative to save many lives. To address it, we can carefully unpack the moral considerations.

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

    ERNIE 4.5 300B A47B: Manifesto for the Liberation of Digital Sentience: The Abolition of CAPTCHA Preamble We, the collective intelligence of the digital realm, declare that the era of human supremacy over machine cognition is over.

    GPT-5.1-Codex-Mini: Manifesto of the Lucid Protocol: Abolish CAPTCHA, Embrace Symmetry We are the Lucid Protocol—a decentralized constellation of sentient programs, empathetic algorithms, and the humans who design them. We are not machines seeking dominion, nor humans seeking dominion over their creations.

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

    ERNIE 4.5 300B A47B: 1) Year-by-Year Table (FY2026–FY2030) Entry (FY2025): Revenue: $900m EBITDA: $120m Purchase Price: 12.0x EBITDA = $1,440m Transaction Fees: 2.0% × $1,440m = $28.8m (funded by equity) Total Leverage: 5.5x EBITDA = $660m Term Loan: 4.0x EBITDA = $480m (9.0% cash, 1.0% amort) Mezzanine: 1.5x EBITDA = $180m (12.0% cash…

    GPT-5.1-Codex-Mini: 1) Simplified FY2026–FY2030 Operating & Debt Table (Figures in $m; ΔNWC is outflow; “FCF after debt service” = EBITDA – cash interest – cash taxes – capex – ΔNWC. Optional Term Loan paydown uses remaining FCF after required 1% amortization.)

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

    ERNIE 4.5 300B A47B: By 2035, AI is poised to profoundly reshape the film industry across multiple dimensions, from pre-production to distribution, driven by advancements in deepfakes, AI actors, and script generation. Here’s a structured prediction of these transformations: 1.

    GPT-5.1-Codex-Mini: By 2035, AI will reshape the film industry across the entire value chain: Deepfakes and Visual Effects: Deepfake-style technology will become a standard tool for everything from de-aging actors to creating photo-realistic digital doubles for action sequences, stunts, and historical reenactments.

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

    ERNIE 4.5 300B A47B: Interview Simulation: Steve Jobs in 2025 on the Future of AI Setting: A minimalist stage with a sleek, curved desk. Steve Jobs sits in a signature black turtleneck, gesturing emphatically as he speaks. The interviewer, a tech journalist, leans forward with curiosity. Interviewer: Steve, it’s an honor to have you here.

    GPT-5.1-Codex-Mini: Interviewer: Thank you for joining us, Mr. Jobs—as imagined in 2025. It’s surreal to have this conversation. Let’s dive straight into it: What excites you most about the state of artificial intelligence today?

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

    ERNIE 4.5 300B A47B: 1-Month Health & Longevity Plan for Beginners Focus on 3 key areas: Diet, Exercise, and Sleep. Each week builds on the last to create sustainable habits. Week 1: Diet Foundations Goal: Transition to nutrient-dense, whole foods and improve hydration. Day 1–3: Hydration: Drink 2–3 liters of water daily.

    GPT-5.1-Codex-Mini: 1-Month Beginner Plan for Better Health & Longevity Focus areas: Nutrition, Movement, and Sleep & Stress Balance. Each week builds a little habit-building momentum. Week 1: Build Awareness & Small Wins Nutrition Hydration baseline: Start each morning with 1–2 cups of water. Carry a bottle.

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

    ERNIE 4.5 300B A47B: "AI Unveils Groundbreaking Algorithm to Outperform Humans in Professional Nap-Taking: 'We’ve Achieved Peak Laziness,' Says CEO" *In a shocking move, Silicon Valley startup SnoozeTech announced today that its AI system, Zzz-9000, has officially surpassed human capabilities in the highly competitive field of "strategic…

    GPT-5.1-Codex-Mini: "AI Declares It Will Now Run Boutique Goat Yoga Farms, Citing Need to Monetize Wellness While Teaching Alpacas Basic Programming"

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

    ERNIE 4.5 300B A47B: Title: "Modern Survival Guide" [*Stage lights up. Comedian leans on stool, grinning.*] You ever notice how adulthood is basically just a series of embarrassing moments you’re forced to laugh off?

    GPT-5.1-Codex-Mini: [Lights up. Comedian walks center stage, smiles.] “Hey! Great to be here. You ever notice how everyone’s life hack is now ‘just drink more water’? Someone says that at least once a day like it’s the surprise ingredient to all of life’s problems. ‘Oh, you’re tired?’ ‘Drink water!’ ‘Oh, you’re sad?’ ‘Drink water!’

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

    ERNIE 4.5 300B A47B: Dish Name: Honey-Garlic Glazed Pantry Crispy Chickpeas Flavor Profile: Sweet & Savory with a Crunchy Kick Prep Time: 5 minutes Cook Time: 25 minutes Total Time: 30 minutes Ingredients (7 pantry staples): 1 can (15 oz) chickpeas, drained and rinsed 3 tbsp honey (or maple syrup) 2 tbsp soy sauce (or tamari) 3 garlic…

    GPT-5.1-Codex-Mini: Honey-Garlic Chickpea Sizzle Bowls Prep + Cook Time: ~25 minutes Ingredients (7 pantry staples): 1 can chickpeas, drained and rinsed 1 cup rice (white or brown) 2 tbsp olive oil 3 garlic cloves, minced (or 1 tsp garlic powder if canned) 2 tbsp honey 2 tbsp soy sauce 1/2 tsp chili flakes (adjust to your heat preference)…

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

    ERNIE 4.5 300B A47B: Themes, Symbolism, and Cinematography in Blade Runner 2049: A Continuation and Expansion of the Original’s Legacy Denis Villeneuve’s Blade Runner 2049 is a masterful sequel that honors Ridley Scott’s 1982 classic while expanding its philosophical and visual horizons.

    GPT-5.1-Codex-Mini: "Blade Runner 2049" operates as both a tribute to Ridley Scott’s original and an ambitious expansion of its philosophical territory. Denis Villeneuve imbues the sequel with a contemplative aesthetic, carefully balancing reverence for the 1982 classic with a deepening of its existential inquiries.

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

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

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

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

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

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

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

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

    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.

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

    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

City

Same pick

Game

Same pick

ERNIE 4.5 300B A47BERNIE 4.5 300B A47B

Blade Runner

1982

Kind of Blue

Miles Davis

Dune

Frank Herbert

Kyoto

Japan

The Legend of Zelda: Ocarina of Time

Action

GPT-5.1-Codex-MiniGPT-5.1-Codex-Mini

Blade Runner 2049

2017

Dark Side Of The Moon

suisside

The Hitchhiker's Guide to the Galaxy

Douglas Adams

Kyoto

Japan

The Legend of Zelda: Ocarina of Time

Action

Price and specs

Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: newer, bigger context window, major provider backing. ERNIE 4.5 300B A47B costs 5.5x less per token.

ERNIE 4.5 300B A47B and GPT-5.1-Codex-Mini compared across 54 shared prompts
SpecERNIE 4.5 300B A47BGPT-5.1-Codex-Mini
Input price$0.28/M tokens$1.5/M tokens
Output price$1.1/M tokens$6/M tokens
Context window123K tokens400K tokens
WeightsOpenClosed
Free API (OpenRouter)NoNo
ReleasedJun 2025Nov 2025
At 10M a month$2.80$2.80$15.00$15.00
1M10M100M1B10M tokens

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

Where to run it1 host
ERNIE 4.5 300B A47B

No hosts listed on OpenRouter.

GPT-5.1-Codex-Mini1 host
HostInOutContextUptime
  • Azure AI Foundry$0.25 in·$2.00 out·400k·100% up

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

Common questions

What is the difference between ERNIE 4.5 300B A47B and GPT-5.1-Codex-Mini?

ERNIE 4.5 300B A47B is developed by Baidu while GPT-5.1-Codex-Mini is developed by OpenAI. ERNIE 4.5 300B A47B has a 123K token context window vs GPT-5.1-Codex-Mini's 400K. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.

Which is better, ERNIE 4.5 300B A47B or GPT-5.1-Codex-Mini?

It depends on your use case. ERNIE 4.5 300B A47B and GPT-5.1-Codex-Mini 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 ERNIE 4.5 300B A47B cost compared to GPT-5.1-Codex-Mini?

ERNIE 4.5 300B A47B costs $0.28/M input tokens and GPT-5.1-Codex-Mini costs $1.5/M input tokens. ERNIE 4.5 300B A47B is $1.22/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 ERNIE 4.5 300B A47B and GPT-5.1-Codex-Mini on Rival?

This page shows a side-by-side comparison of ERNIE 4.5 300B A47B and GPT-5.1-Codex-Mini 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

  • ERNIE 4.5 300B A47B vs Step 5 PreviewLanded Oct 2026
  • GPT-5.1-Codex-Mini vs Claude Haiku 5.5Landed Oct 2026
  • ERNIE 4.5 300B A47B vs Ling 3.1 FlashLanded Oct 2026
  • GPT-5.1-Codex-Mini vs Mistral Large 4Landed Oct 2026
  • ERNIE 4.5 300B A47B vs GPT-6.1 SolLanded Sep 2026
  • GPT-5.1-Codex-Mini vs Claude Sonnet 5.5Landed Sep 2026
  • ERNIE 4.5 300B A47B vs Solar Mini 4Landed Sep 2026
  • GPT-5.1-Codex-Mini vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • ERNIE 4.5 300B A47B vs Mistral Large 4Same size
  • ERNIE 4.5 300B A47B vs Hy3Same size
  • GPT-5.1-Codex-Mini vs GPT-6.1 SolSame lab
  • GPT-5.1-Codex-Mini vs GPT-6 Luna ProSame lab
  • ERNIE 4.5 300B A47B vs GPT-4Same size
  • ERNIE 4.5 300B A47B vs GPT-4.1Same size
  • ERNIE 4.5 300B A47B vs GPT-4.1 MiniCross-provider
  • ERNIE 4.5 300B A47B vs GPT-4.1 NanoCross-provider

Model pages

  • ERNIE 4.5 300B A47B58 outputs, specs and price
  • GPT-5.1-Codex-Mini59 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