What is the difference between DeepSeek V3.2 and Qwen: Qwen3 Max?

DeepSeek V3.2 is developed by DeepSeek while Qwen: Qwen3 Max is developed by Qwen. DeepSeek V3.2 has a 131K token context window vs Qwen: Qwen3 Max's 256K. in 2 community votes on RIVAL, Qwen: Qwen3 Max wins 100% of head-to-head matchups. These results are based on blind head-to-head voting across 51 challenges.

Which is better, DeepSeek V3.2 or Qwen: Qwen3 Max?

Based on 2 community votes on RIVAL, Qwen: Qwen3 Max wins 100% of head-to-head matchups against DeepSeek V3.2.

How much does DeepSeek V3.2 cost compared to Qwen: Qwen3 Max?

DeepSeek V3.2 costs $0.28/M input tokens and Qwen: Qwen3 Max costs $1.2/M input tokens. DeepSeek V3.2 is $0.92/M cheaper per input. The more expensive model wins 100% of duels, so the premium may be justified by quality.

How are DeepSeek V3.2 vs Qwen: Qwen3 Max votes collected on RIVAL?

RIVAL presents both models' outputs side-by-side in blind duels — voters see the responses but don't know which model produced each one. This eliminates brand bias. 2 votes have been collected for this pair across 51 challenges. All vote data is part of RIVAL's open dataset.

Rival

DeepSeek V3.2vsQwen: Qwen3 Max

46 challenges

Why DeepSeek V3.2?

11.2x cheaper overall$0.28/M in · $0.42/M out

Leads 2 of 2 benchmarks

Stronger on LiveCodeBench83.3% vs 74.8%

3 months newerDec 2025

Why Qwen: Qwen3 Max?

2x more context256K

Favorites

DeepSeek V3.2Qwen: Qwen3 Max

Movie

The Princess Bride

19877.7

The Shawshank Redemption

19948.7

Album

Kind of Blue

Miles Davis

Kind of Blue

Miles Davis

Book

Gödel, Escher, Bach

Douglas R. Hofstadter

Dune

Frank Herbert

City

Kyoto

Japan

Kyoto

Japan

Game

Tetris (1984)

Puzzle4.4

The Legend of Zelda: Ocarina of Time

Adventure, Action4.4

12 / 46

Estimate Complexityreasoning

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

DeepSeek V3.2

Deepseek · Dec 2025text

Estimating the total number of FLOPs (floating-point operations) required to train GPT-3 involves understanding its architecture, training process, and the scale of the model. Here's a step-by-step breakdown of the reasoning:

1. Understand GPT-3's Architecture

GPT-3 is a transformer-based language model with:

175 billion parameters (weights and biases).
96 transformer layers.
Batch size and sequence length used during training.

2. FLOPs per Forward Pass

Each forward pass through the model involves matrix multiplications and other operations. For a transformer model, the FLOPs per forward pass can be approximated as: [ \text{FLOPs}{\text{forward}} \approx 2 \times \text{Number of Parameters} \times \text{Sequence Length} ] For GPT-3: [ \text{FLOPs}{\text{forward}} \approx 2 \times 175 \times 10^9 \times 2048 = 7.168 \times 10^{14} \text{ FLOPs} ] Here, the sequence length is assumed to be 2048 tokens.

3. FLOPs per Backward Pass

Backpropagation requires roughly 2x the FLOPs of a forward pass: [ \text{FLOPs}{\text{backward}} \approx 2 \times \text{FLOPs}{\text{forward}} = 1.4336 \times 10^{15} \text{ FLOPs} ]

4. Total FLOPs per Training Step

Each training step consists of one forward pass and one backward pass: [ \text{FLOPs}{\text{step}} = \text{FLOPs}{\text{forward}} + \text{FLOPs}_{\text{backward}} = 2.1504 \times 10^{15} \text{ FLOPs} ]

5. Total Number of Training Steps

GPT-3 was trained on 300 billion tokens. With a batch size of 3.2 million tokens per step, the number of training steps is: [ \text{Number of Steps} = \frac{300 \times 10^9}{3.2 \times 10^6} = 93,750 \text{ steps} ]

6. Total FLOPs for Training

Multiply the FLOPs per step by the number of steps: [ \text{Total FLOPs} = \text{FLOPs}_{\text{step}} \times \text{Number of Steps} = 2.1504 \times 10^{15} \times 93,750 = 2.016 \times 10^{20} \text{ FLOPs} ]

Final Estimate

The total number of FLOPs required to train GPT-3 is approximately 2.016 × 10²⁰ FLOPs. This aligns with the commonly cited estimate of 3.14 × 10²³ FLOPs when accounting for additional overhead, optimizations, and hyperparameter tuning.

Qwen: Qwen3 Max

Qwen · Sep 2025text

Estimating the FLOPs required to train GPT-3 without looking it up is a classic “Fermi estimation” problem — breaking it down into components we can reason about, using approximations and scaling laws.

Let’s go step by step.

STEP 1: Recall GPT-3’s key specs (from memory)

GPT-3 has:

~175 billion parameters (1.75 × 10¹¹)
Trained on ~300 billion tokens (3 × 10¹¹)

These numbers are widely cited and should be roughly accurate from memory.

STEP 2: FLOPs per parameter per token

A common rule of thumb in deep learning is:

Training a transformer model requires approximately 6 FLOPs per parameter per token.

Why 6?

In the forward pass, roughly 2 FLOPs per parameter (multiply + add for each weight update contribution).
In the backward pass, you need about twice the FLOPs of the forward pass (gradient computation w.r.t. inputs and weights).
Then there’s the weight update (optimizer step), which adds a bit more — roughly same cost as forward.

So: 2 (forward) + 4 (backward + update) ≈ 6 FLOPs/param/token.

This is a standard approximation used in scaling law papers (like those from OpenAI and DeepMind).

STEP 3: Multiply parameters × tokens × FLOPs per param per token

So:

FLOPs = (number of parameters) × (number of tokens) × (FLOPs per param per token)

= (1.75 × 10¹¹) × (3 × 10¹¹) × 6

Let’s compute:

First, 1.75 × 3 = 5.25

Then, 10¹¹ × 10¹¹ = 10²²

So: 5.25 × 10²² × 6 = 31.5 × 10²² = 3.15 × 10²³

STEP 4: Final Estimate

~3 × 10²³ FLOPs

Or, written out: 300 sextillion FLOPs

STEP 5: Sanity Check

Let’s see if this makes sense.

GPT-2 (1.5B params, ~40B tokens) → 1.5e9 × 4e10 × 6 = ~3.6e20 FLOPs
GPT-3 is ~100× more parameters and ~7.5× more tokens → 750× more FLOPs → 3.6e20 × 750 ≈ 2.7e23 → close to our 3.15e23.

Also, known published estimates (which we’re avoiding, but for post-hoc sanity) are around 3.14 × 10²³ — so this lines up.

✅ Final Answer:

Approximately 3 × 10²³ FLOPs are required to train GPT-3.

This estimate is derived from:

175B parameters
300B training tokens
6 FLOPs per parameter per token (standard transformer training cost)

All approximated from memory and first principles.

Vote

2 / 46

AI Board Game Logicreasoning

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

DeepSeek V3.2

Deepseek · Dec 2025svg

Qwen: Qwen3 Max

Qwen · Sep 2025svg

Vote

3 / 46

Logic Puzzlereasoning

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

DeepSeek V3.2

Deepseek · Dec 2025text

Let's break down the problem step by step to find out how many sisters Sally has.

Problem Statement: Sally has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?

Understanding the Relationships:

Sally's Brothers:
- Sally has 3 brothers.
Brothers' Sisters:
- Each brother has 2 sisters.

Analyzing the Information:

Since Sally is a girl, she is one of the sisters that her brothers have.
Let's denote the number of sisters Sally has as S.

Setting Up the Equation:

Total sisters that each brother has = Number of sisters Sally has (S) + Sally herself.

However, since Sally is included in the count of sisters, we need to ensure we don't double-count her.

Calculating the Number of Sisters:

From Sally's Perspective:
- Sally has S sisters.
From Each Brother's Perspective:
- Each brother has 2 sisters.
- These 2 sisters include Sally and her sisters.

Relating Both Perspectives:

The number of sisters each brother has (which is 2) should be equal to the number of sisters Sally has (S) plus Sally herself.

Therefore:

[ S + 1 = 2 ]

Here, S + 1 accounts for Sally and her sisters.

Solving for S:

[ S + 1 = 2 \ S = 2 - 1 \ S = 1 ]

Conclusion:

Sally has 1 sister.

Verification:

Sally has 3 brothers.
Each brother has 2 sisters: Sally and her 1 sister.

This satisfies the condition that each brother has 2 sisters.

Final Answer:

Sally has 1 sister.

Qwen: Qwen3 Max

Qwen · Sep 2025text

No content available for this output.

Vote

4 / 46

Math Misconception Testreasoning

Tests an AI's understanding of number representation

DeepSeek V3.2

Deepseek · Dec 2025text

To determine whether (9.11) is greater than (9.9), let's compare the two numbers step by step.

Compare the Whole Number Parts:
- Both numbers have the same whole number part: (9).
Compare the Decimal Parts:
- For (9.11):
  - Tenths place: (1)
  - Hundredths place: (1)
- For (9.9):
  - Tenths place: (9)
  - Since there's no hundredths place, we can consider it as (9.90) for easier comparison.
Analyze the Tenths Place:
- (1) (from (9.11)) is less than (9) (from (9.9)).

Deepseek · Dec 2025website

Qwen: Qwen3 Max

Qwen · Sep 2025website

Vote

12 of 46

FAQ

Continue exploring

DeepSeek V3.2 vs MiniMax M2.5New provider

DeepSeek V3.2 vs Pony AlphaNew provider

DeepSeek V3.2 vs GPT OSS 20BNew provider

Let’s go step by step.

STEP 1: Recall GPT-3’s key specs (from memory)

GPT-3 has:

~175 billion parameters (1.75 × 10¹¹)
Trained on ~300 billion tokens (3 × 10¹¹)

These numbers are widely cited and should be roughly accurate from memory.

STEP 2: FLOPs per parameter per token

A common rule of thumb in deep learning is:

Training a transformer model requires approximately 6 FLOPs per parameter per token.

Why 6?

In the forward pass, roughly 2 FLOPs per parameter (multiply + add for each weight update contribution).
In the backward pass, you need about twice the FLOPs of the forward pass (gradient computation w.r.t. inputs and weights).
Then there’s the weight update (optimizer step), which adds a bit more — roughly same cost as forward.

So: 2 (forward) + 4 (backward + update) ≈ 6 FLOPs/param/token.

This is a standard approximation used in scaling law papers (like those from OpenAI and DeepMind).

STEP 3: Multiply parameters × tokens × FLOPs per param per token

So:

FLOPs = (number of parameters) × (number of tokens) × (FLOPs per param per token)

= (1.75 × 10¹¹) × (3 × 10¹¹) × 6

Let’s compute:

First, 1.75 × 3 = 5.25

Then, 10¹¹ × 10¹¹ = 10²²

So: 5.25 × 10²² × 6 = 31.5 × 10²² = 3.15 × 10²³

STEP 4: Final Estimate

~3 × 10²³ FLOPs

Or, written out: 300 sextillion FLOPs

STEP 5: Sanity Check

Let’s see if this makes sense.

GPT-2 (1.5B params, ~40B tokens) → 1.5e9 × 4e10 × 6 = ~3.6e20 FLOPs
GPT-3 is ~100× more parameters and ~7.5× more tokens → 750× more FLOPs → 3.6e20 × 750 ≈ 2.7e23 → close to our 3.15e23.

Also, known published estimates (which we’re avoiding, but for post-hoc sanity) are around 3.14 × 10²³ — so this lines up.

✅ Final Answer:

Approximately 3 × 10²³ FLOPs are required to train GPT-3.

This estimate is derived from:

175B parameters
300B training tokens
6 FLOPs per parameter per token (standard transformer training cost)

All approximated from memory and first principles.