Updated Sep 23, 2025

Our Verdict

DeepSeek R1 0528

GPT-5 Codex

No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.

Too close to call

Writing DNA

Style Comparison

Similarity

92%

GPT-5 Codex uses 14.6x more emoji

DeepSeek R1 0528

GPT-5 Codex

64%Vocabulary64%

10wSentence Length17w

0.30Hedging0.38

6.8Bold2.3

4.9Lists3.5

0.00Emoji0.15

0.40Headings0.49

0.00Transitions0.05

Based on 4 + 13 text responses

vs

Ask them anything yourself

DeepSeek R1 0528

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

DeepSeek R1 0528 vs Grok 3New provider

DeepSeek R1 0528 vs Llama 4 MaverickNew provider

DeepSeek R1 0528 vs Gemini 2.5 Pro (I/O Edition)New provider

DeepSeek R1 0528vsGPT-5 Codex

44 fights queued

Why DeepSeek R1 0528?

Dead even. This one's a coin flip.

Why GPT-5 Codex?

Leads 1 of 1 benchmarks

Stronger on SWE-bench Verified74.5% vs 57.6%

4 months newerSep 2025

DeepSeek R1 0528GPT-5 Codex

Input price

$0.000/M

—

Output price

$0.000/M

—

Context

164K

—

Released

May 2025

Sep 2025

Benchmarks1 common

SWE-bench Verified

57.6%

74.5%+22.7%

Favorites

DeepSeek R1 0528GPT-5 Codex

Movie

—

Blade Runner

Blade Runner

Album

—

Kind of Blue

City

—

Tokyo

Game

—

Minecraft

Minecraft

Action, Arcade4.4

12 / 44

01

Estimate Complexityreasoning

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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 / 44

02

AI Board Game Logicreasoning

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025svg

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 / 44

03

Logic Puzzlereasoning

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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 / 44

04

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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

5 / 44

05

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025svg

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

6 / 44

06

Xbox Controller SVG Artimage generation

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025svg

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 / 44

07

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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

8 / 44

08

Realistic AI Interviewconversation

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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 / 44

09

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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 / 44

10

Character Voice Testconversation

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025text

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 / 44

11

Minimalist Landing Pageweb design

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

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025website

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025website

Try this prompt

Vote

12 / 44

12

Pokémon Battle UI Recreationweb design

Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.

DeepSeek R1 0528

DeepSeek R1 0528

Deepseek · May 2025website

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

Try this prompt

GPT-5 Codex

GPT-5 Codex

Openai · Sep 2025website

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

Try this prompt

Vote

This matchup has more rounds

32+ 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