What is the difference between GPT-5 Codex and Qwen3 235B A22B?

GPT-5 Codex is developed by OpenAI while Qwen3 235B A22B is developed by Qwen. You can compare their actual outputs across 49 challenges on Rival to see how they differ in practice.

Which is better, GPT-5 Codex or Qwen3 235B A22B?

It depends on your use case. GPT-5 Codex and Qwen3 235B A22B each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 49 challenges so you can judge which fits your needs best.

How can I compare GPT-5 Codex and Qwen3 235B A22B on Rival?

This page shows a side-by-side comparison of GPT-5 Codex and Qwen3 235B A22B across shared challenges. You can vote on which model produced the better output, and Pro users can create custom challenges to test both models with their own prompts.

Rival

Updated Sep 23, 2025

GPT-5 CodexvsQwen3 235B A22B

44 fights queued

Why GPT-5 Codex?

Leads 1 of 1 benchmarks

Stronger on SWE-bench Verified74.5% vs 61.7%

5 months newerSep 2025

Why Qwen3 235B A22B?

Dead even. This one's a coin flip.

GPT-5 CodexQwen3 235B A22B

Context

—

33K

Released

Sep 2025

Apr 2025

Benchmarks1 common

SWE-bench Verified

74.5%+17.2%

61.7%

Favorites

GPT-5 CodexQwen3 235B A22B

Movie

Blade Runner

19827.9

The Godfather

19728.7

Album

Kind of Blue

Miles Davis

Sgt Peppers Lonely Hearts Club Band

The Beatles

Book

—

Nineteen Eighty-Four

George Orwell

City

Tokyo

Japan

Istanbul

Turkey

Game

Minecraft

Action, Arcade4.4

The Legend of Zelda: Ocarina of Time

Adventure, Action4.4

12 / 44

Estimate Complexityreasoning

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

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.

GPT-5 Codex vs Qwen3 235B A22B

Which is better, GPT-5 Codex or Qwen3 235B A22B?