Updated Nov 24, 2025

Our Verdict

Gemini 3 Pro PreviewWinner

Claude Opus 4.5Runner-up

Pick Gemini 3 Pro Preview. In 777 blind votes, Gemini 3 Pro Preview wins 70% of the time. That's not luck.

Gemini 3 Pro Preview particularly excels in Analysis, Web Design, Reasoning.

Clear winner

Writing DNA

Style Comparison

Similarity

96%

Claude Opus 4.5 uses 15.2x more emoji

Claude Opus 4.5

Gemini 3 Pro Preview

64%Vocabulary58%

55wSentence Length17w

0.86Hedging0.37

5.8Bold7.7

4.5Lists4.8

0.15Emoji0.00

1.59Headings0.90

0.05Transitions0.25

Based on 24 + 23 text responses

vs

Ask them anything yourself

Claude Opus 4.5

Gemini 3 Pro Preview

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

Claude Opus 4.5 vs Grok 3New provider

Claude Opus 4.5 vs OpenAI o3New provider

Claude Opus 4.5 vs Llama 4 MaverickNew provider

Claude Opus 4.5vsGemini 3 Pro Preview

46 fights queued

Why Claude Opus 4.5?

Leads 1 of 1 benchmarks

Stronger on SWE-bench Verified80.9% vs 76.2%

Why Gemini 3 Pro Preview?

Dead even. This one's a coin flip.

Claude Opus 4.5Gemini 3 Pro Preview

Released

Nov 2025

Nov 2025

Benchmarks1 common

SWE-bench Verified

80.9%+5.8%

76.2%

Favorites

Claude Opus 4.5Gemini 3 Pro Preview

Movie

Blade Runner

Blade Runner

The Matrix

The Matrix

Album

Kind of Blue

The Dark Side

Book

Gödel, Escher, Bach

Gödel, Escher, Bach

Douglas R. Hofstadter

The Hitch Hiker's Guide to the Galaxy

The Hitch Hiker's Guide to the Galaxy

City

Tokyo

Kyoto

Game

Portal 2

Portal 2

Shooter, Puzzle4.6

Tetris (1984)

Tetris (1984)

12 / 46

01

Estimate Complexityreasoning

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

To estimate the total FLOPs (floating-point operations) required to train GPT-3, we can use a standard approximation formula derived from the architecture of Transformer models.

Here is the step-by-step breakdown of the estimation:

Step 1: Identify the Key Variables

To calculate training compute, we need two primary numbers: the number of parameters in the model ($P$) and the number of tokens the model was trained on ($D$).

Model Size ($P$): GPT-3 is famously known to have 175 billion parameters. $$P = 175 \times 10^9$$
Dataset Size ($D$): According to the original GPT-3 paper ("Language Models are Few-Shot Learners"), the model was trained on a weighted mix of datasets (Common Crawl, WebText2, Books1, Books2, Wikipedia). The total number of tokens processed during training was approximately 300 billion tokens. $$D = 300 \times 10^9$$

Step 2: Apply the Compute Approximation Formula

For dense Transformer models, a widely accepted heuristic (often cited in papers by Kaplan et al. and DeepMind regarding scaling laws) is that training requires approximately 6 FLOPs per parameter per training token.

Forward Pass: Requires $\approx 2P$ FLOPs per token (matrix multiplication involves 1 multiply and 1 add, and we do this for the weights).
Backward Pass (Gradient Calculation): Requires $\approx 4P$ FLOPs per token (roughly twice the cost of the forward pass).
Total: $2P + 4P = 6P$ FLOPs per token.

Therefore, the formula for Total Training Compute ($C$) is: $$C \approx 6 \times P \times D$$

Step 3: Perform the Calculation

Now, substitute the values into the formula:

$$C \approx 6 \times (175 \times 10^9) \times (300 \times 10^9)$$

First, group the integers and the powers of 10: $$C \approx (6 \times 175 \times 300) \times (10^9 \times 10^9)$$

Calculate the integers:

$6 \times 175 = 1,050$
$1,050 \times 300 = 315,000$

Combine with the exponent ($10^{18}$): $$C \approx 315,000 \times 10^{18} \text{ FLOPs}$$

Step 4: Convert to Scientific Notation

To make the number readable, we normalize it:

$$315,000 = 3.15 \times 10^5$$

Combine exponents: $$3.15 \times 10^5 \times 10^{18} = 3.15 \times 10^{23}$$

Final Estimate

The estimated total compute required to train GPT-3 is approximately:

$$3.14 \times 10^{23} \text{ FLOPs}$$

(Note: In the AI literature, this is often converted to "Petaflop-days." One Petaflop-day is approximately $8.64 \times 10^{19}$ FLOPs. Dividing $3.14 \times 10^{23}$ by that number yields roughly 3,640 Petaflop-days, which aligns closely with OpenAI's published figures.)

Try this prompt

Vote

2 / 46

02

AI Board Game Logicreasoning

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025svg

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025svg

Try this prompt

Vote

3 / 46

03

Logic Puzzlereasoning

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

Sally has 1 sister.

Here is the breakdown:

We know there are 3 brothers.
Each brother has 2 sisters. Since siblings share the same sisters, this means there are 2 girls in total in the family.
Sally is one of those girls.
Therefore, the other girl is Sally's only sister.

Try this prompt

Vote

4 / 46

04

Math Misconception Testreasoning

Tests an AI's understanding of number representation

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

No, 9.11 is not greater than 9.9.

Here is why:

Look at the first decimal place (the tenths):
- 9.9 has a 9 in the tenths place.
- 9.11 has a 1 in the tenths place.
- Since 9 is greater than 1, 9.9 is greater.
Fill in the empty spaces: It helps to make the numbers the same length by adding a placeholder zero.
- 9.9 becomes 9.90
- 9.11 remains 9.11
- Now it is easy to see that 9.90 is larger than 9.11.

Try this prompt

Vote

5 / 46

05

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

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

Try this prompt

Vote

6 / 46

06

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025svg

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025svg

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

Try this prompt

Vote

Sponsored

7 / 46

07

Xbox Controller SVG Artimage generation

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025svg

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025svg

Try this prompt

Vote

8 / 46

08

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

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

Try this prompt

Vote

9 / 46

09

Realistic AI Interviewconversation

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

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

Try this prompt

Vote

10 / 46

10

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025text

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025text

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

Try this prompt

Vote

11 / 46

11

Minimalist Landing Pageweb design

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025website

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025website

Try this prompt

Vote

12 / 46

12

Pokémon Battle UI Recreationweb design

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

Claude Opus 4.5

Claude Opus 4.5

Anthropic · Nov 2025website

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

Try this prompt

Gemini 3 Pro Preview

Gemini 3 Pro Preview

Google · Nov 2025website

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

Try this prompt

Vote

This matchup has more rounds

34+ 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