Updated Sep 23, 2025

Our Verdict

GPT-5 Codex

GPT-4o miniRunner-up

No community votes yet. On paper, GPT-5 Codex has the edge — bigger model tier, newer.

Too close to call

Writing DNA

Style Comparison

Similarity

100%

GPT-5 Codex uses 14.6x more emoji

GPT-4o mini

GPT-5 Codex

54%Vocabulary64%

18wSentence Length17w

0.84Hedging0.38

3.8Bold2.3

3.3Lists3.5

0.00Emoji0.15

1.03Headings0.49

0.23Transitions0.05

Based on 22 + 13 text responses

vs

Ask them anything yourself

GPT-4o mini

GPT-5 Codex

279 AI models invented the same fake scientist.

We read every word. 250 models. 2.14 million words. This is what we found.

AI Hallucination Index 2026

Free preview13 of 58 slides

Download the free preview or get all 58 slides for $49

FAQ

Common questions

Keep going

GPT-5 Codex vs Gemini 2.5 Pro Preview 06-05New provider

GPT-4o mini vs Grok 3New provider

GPT-4o mini vs Llama 4 MaverickNew provider

GPT-4o minivsGPT-5 Codex

38 fights queued

Why GPT-4o mini?

Dead even. This one's a coin flip.

Why GPT-5 Codex?

14 months newerSep 2025

GPT-4o miniGPT-5 Codex

Input price

$0.15/M

—

Output price

$0.60/M

—

Context

128K

—

Released

Jul 2024

Sep 2025

Favorites

GPT-4o miniGPT-5 Codex

Movie

Inception

Inception

Blade Runner

Blade Runner

Album

Abbey Road

Kind of Blue

Book

Nineteen Eighty-Four

Nineteen Eighty-Four

—

City

Kyoto

Tokyo

Game

The Legend of Zelda: Breath of the Wild

The Legend of Zelda: Breath of the Wild

Adventure, Action4.5

Minecraft

Minecraft

Action, Arcade4.4

12 / 38

01

Estimate Complexityreasoning

Tests an AI's ability to make educated estimates based on technical knowledge

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

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).

Step 2 – Relate parameters, tokens, and FLOPs

For dense transformers, almost all computation comes from matrix multiplies.
A practical rule (derived by counting multiply–adds in the attention and MLP blocks, and accounting for the backward pass) is:

[ \text{Training FLOPs} \approx 6 \times (\text{number of parameters}) \times (\text{number of tokens}) ]

Here’s the intuition:

Forward pass: Each parameter contributes one multiply and one add → about (2) FLOPs per parameter per token.
Backward pass: Computing gradients with respect to activations and weights requires roughly twice the forward cost (two more matrix multiplies of comparable size).
So total ≈ (3) times the forward cost → (3 \times 2 = 6) FLOPs per parameter per token.

(The softmax, layernorm, activation costs are much smaller and get absorbed into this constant.)

Step 3 – Plug in the GPT‑3 values

[ \text{FLOPs} \approx 6 \times (1.75\times 10^{11}) \times (3.0 \times 10^{11}) ]

[ = 6 \times 5.25 \times 10^{22} = 31.5 \times 10^{22} \approx 3.15 \times 10^{23} \text{ FLOPs} ]

Step 4 – Interpret

So, training GPT‑3 to completion requires on the order of (3 \times 10^{23}) floating-point operations.
That estimate aligns with detailed breakdowns of transformers and is accurate to within tens of percent, which is sufficient for order-of-magnitude comparisons.

Try this prompt

Vote

2 / 38

02

AI Board Game Logicreasoning

Tests an AI's ability to understand game rules and strategy

GPT-4o mini

GPT-4o mini

Openai · Jul 2024svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025svg

Try this prompt

Vote

3 / 38

03

Logic Puzzlereasoning

Tests an AI's ability to solve a simple but potentially confusing logic puzzle

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

Sally has 1 sister.

Try this prompt

Vote

4 / 38

04

Math Misconception Testreasoning

Tests an AI's understanding of number representation

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

No. Since 9.11 is equal to 9.110 and 9.9 is equal to 9.900, we see that 0.110 < 0.900, so 9.11 is less than 9.9.

Try this prompt

Vote

5 / 38

05

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

6 / 38

06

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

GPT-4o mini

GPT-4o mini

Openai · Jul 2024svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

Sponsored

7 / 38

07

Xbox Controller SVG Artimage generation

Tests an AI's ability to create detailed SVG illustrations of gaming hardware

GPT-4o mini

GPT-4o mini

Openai · Jul 2024svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025svg

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

8 / 38

08

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

9 / 38

09

Realistic AI Interviewconversation

Tests an AI's ability to simulate personalities and predict future trends

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

10 / 38

10

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

11 / 38

11

Character Voice Testconversation

Tests an AI's ability to write in distinct character voices

GPT-4o mini

GPT-4o mini

Openai · Jul 2024text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025text

Nothing here. The model returned empty. We stared at it for a while.

Try this prompt

Vote

12 / 38

12

Minimalist Landing Pageweb design

Tests an AI's ability to generate a complete, working landing page

GPT-4o mini

GPT-4o mini

Openai · Jul 2024website

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025website

Try this prompt

Vote

This matchup has more rounds

26+ 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