Skip to content
Rival
Models
Compare
Best ForArenaPricing
Sign Up
Sign Up

We compare AI models for a living. On purpose. We chose this.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Find Your Model
  • Image Generation
  • Audio Comparison
  • Best AI For...
  • Pricing
  • Challenges

Discover

  • Insights
  • Research
  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • Rival Datasets

Connect

  • Methodology
  • Sponsor a Model
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival · Built at hours no one should be awake, on hardware we don't own
Bert-Nebulon Alpha vs OpenAI o4-mini: Which Is Better? [2026 Comparison]
Rival
Models
Compare
Best ForArenaPricing
Sign Up
Sign Up
  1. Home
  2. Compare
  3. Bert-Nebulon Alpha vs OpenAI o4-mini
Updated Nov 24, 2025

Bert-Nebulon Alpha vs OpenAI o4-mini

Compare Bert-Nebulon Alpha by OpenRouter against OpenAI o4-mini by OpenAI, tested across 24 shared challenges. Updated April 2026.

Which is better, Bert-Nebulon Alpha or OpenAI o4-mini?

Bert-Nebulon Alpha and OpenAI o4-mini are both competitive models. Compare their real outputs side by side below.

Key Differences Between Bert-Nebulon Alpha and OpenAI o4-mini

Bert-Nebulon Alpha is made by openrouter while OpenAI o4-mini is from openai.

Loading share button...

Bert-Nebulon AlphavsOpenAI o4-mini

24 fights queued

Bert-Nebulon Alpha logo

Why Bert-Nebulon Alpha?

7 months newerNov 2025
OpenAI o4-mini logo

Why OpenAI o4-mini?

Dead even. This one's a coin flip.
Bert-Nebulon AlphaOpenAI o4-mini
Input price
—
$1.10/M
Output price
—
$4.40/M
Released
Nov 2025
Apr 2025

Favorites

Bert-Nebulon AlphaOpenAI o4-mini
Movie
—
The Shawshank Redemption

The Shawshank Redemption

19948.7
12 / 24
01

Estimate Complexityreasoning

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

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text

Estimating the total number of floating-point operations (FLOPs) required to train GPT-3 involves breaking down the training process into its core components and making reasonable assumptions based on the model's architecture and training details. Here's a step-by-step breakdown:


1. Key Parameters of GPT-3

GPT-3 has the following key specifications (from the paper or known details):

  • Model size: 175 billion parameters (weights).
  • Training tokens: ~300 billion tokens (from the paper).
  • Batch size: ~3.2 million tokens per batch (1,536 sequences × 2,048 tokens).
  • Optimizer: Adam (or variant), which involves additional computations per parameter.
  • Training steps: ~300 billion tokens / 3.2 million tokens per batch ≈ 93,750 steps.

2. FLOPs per Forward Pass

For a transformer model, the bulk of computation comes from:

  • Matrix multiplications in the attention and feed-forward layers.
  • Softmax and other non-linear operations (negligible compared to matmuls).

Attention Layer FLOPs

For a single attention head:

  • Query-Key-Value projections: 3 × (d_model × d_k) per token.
  • Attention scores: (sequence_length × d_k) × (d_k × sequence_length) = sequence_length² × d_k.
  • Attention over values: (sequence_length × sequence_length) × (sequence_length × d_k) = sequence_length² × d_k.
  • Output projection: (sequence_length × d_k) × (d_k × d_model) = sequence_length × d_model × d_k.

For h heads, this scales linearly. For GPT-3:

  • d_model = 12,288 (hidden size).
  • h = 96 heads.
  • d_k = d_model / h = 128.
  • Sequence length = 2,048 tokens.

Total FLOPs per attention layer:

  • Projections: 3 × (2,048 × 12,288 × 128) ≈ 9.66 × 10⁹.
  • Attention scores: 96 × (2,048² × 128) ≈ 5.15 × 10¹⁰.
  • Attention over values: 96 × (2,048² × 128) ≈ 5.15 × 10¹⁰.
  • Output projection: 2,048 × 12,288 × 128 ≈ 3.22 × 10⁹.
  • Total per attention layer: ~1.16 × 10¹¹ FLOPs.

GPT-3 has 96 layers, so total attention FLOPs per forward pass: 96 × 1.16 × 10¹¹ ≈ 1.11 × 10¹³ FLOPs.

Feed-Forward Layer FLOPs

Each feed-forward layer has two linear transformations:

  • First: (2,048 × 12,288) × (12,288 × 4 × 12,288) ≈ 1.23 × 10¹² FLOPs.
  • Second: (2,048 × 4 × 12,288) × (4 × 12,288 × 12,288) ≈ 1.23 × 10¹² FLOPs.
  • Total per feed-forward layer: ~2.46 × 10¹² FLOPs.

For 96 layers: 96 × 2.46 × 10¹² ≈ 2.36 × 10¹⁴ FLOPs.

Embedding and Output Layers

  • Embedding lookup: negligible (2,048 × 12,288 ≈ 2.5 × 10⁷ FLOPs).
  • Final projection: 2,048 × 12,288 × vocab_size (50,257) ≈ 1.26 × 10¹² FLOPs.

Total Forward Pass FLOPs

Attention + Feed-forward + Output ≈ 1.11 × 10¹³ + 2.36 × 10¹⁴ + 1.26 × 10¹² ≈ 2.48 × 10¹⁴ FLOPs.


3. FLOPs per Backward Pass

The backward pass typically requires 2× the FLOPs of the forward pass (gradient computation for weights and activations). Thus: Backward pass ≈ 2 × 2.48 × 10¹⁴ ≈ 4.96 × 10¹⁴ FLOPs.


4. Optimizer FLOPs (Adam)

Adam involves:

  • Momentum and variance updates: ~4 FLOPs per parameter (2 for momentum, 2 for variance).
  • Weight update: ~2 FLOPs per parameter.
  • Total per parameter: ~6 FLOPs.

For 175 billion parameters: 175 × 10⁹ × 6 ≈ 1.05 × 10¹² FLOPs per step.


5. Total FLOPs per Training Step

Forward + Backward + Optimizer ≈ 2.48 × 10¹⁴ + 4.96 × 10¹⁴ + 1.05 × 10¹² ≈ 7.45 × 10¹⁴ FLOPs per step.


6. Total Training FLOPs

Total steps = 93,750. Total FLOPs = 93,750 × 7.45 × 10¹⁴ ≈ 6.98 × 10¹⁹ FLOPs.


7. Adjustments and Simplifications

  • Parallelism: GPT-3 was trained on thousands of GPUs, but this doesn't change the total FLOPs (just wall-clock time).
  • Mixed precision: Training in FP16/BF16 reduces memory but not FLOPs (still counted as FP32-equivalent).
  • Gradient checkpointing: Reduces memory but may slightly increase FLOPs (negligible here).
  • Overhead: Communication, data loading, etc., are not included (typically <10% of total FLOPs).

8. Final Estimate

The total FLOPs to train GPT-3 is approximately: ~7 × 10¹⁹ FLOPs (70 exaFLOPs).

This aligns with independent estimates (e.g., Epoch AI's analysis suggests ~3.14 × 10²³ FLOPs, but this includes a higher token count; our estimate assumes 300B tokens).


Key Takeaways

  1. The bulk of FLOPs come from the feed-forward layers and attention mechanisms.
  2. The backward pass is 2× the forward pass in FLOPs.
  3. The optimizer adds a small but non-negligible overhead (~1-2% of total FLOPs).
  4. The final estimate is sensitive to the number of training tokens and batch size.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text

Here's a back‐of‐the‐envelope derivation that gets us into the right ballpark (∼10²³ FLOPs total):

  1. Model size
    • GPT–3 "175 B" has about P ≃1.75×10¹¹ parameters.

  2. Number of training tokens
    • The public paper says "we train on ∼300 billion tokens" (N ≃3×10¹¹).

  3. FLOPs per token
    • Every forward+backward through the network touches all parameters.
    • Rough rule of thumb: you need O(6) FLOPs per parameter per token
    (a couple multiplies/adds in the forward pass, a similar count in the backward, and some small extra for optimizer updates). • So 6 × P FLOPs/token ≃ 6×1.75×10¹¹ ≃1.05×10¹² FLOPs/token.

  4. Total FLOPs
    • Multiply FLOPs/token by number of tokens:
    Total ≃ (1.05×10¹² FLOPs/token) × (3×10¹¹ tokens)
    ≃ 3.15×10²³ FLOPs.

  5. Sanity check
    • 3×10²³ FLOPs is 3×10⁵ PFLOP·days (since 1 PFLOP/s×86 400 s ≈ 8.6×10¹⁹ FLOPs/day).
    • That's a few thousand GPU‐days on a modern accelerator cluster—consistent with the published "thousands of V100‐GPU days" statement.

Bottom‐line estimate: on the order of 10²³–10²⁴ floating‐point operations to train GPT‑3 175 B from scratch.

Try this prompt
Vote
2 / 24
02

Logic Puzzlereasoning

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

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text

Alright, let's tackle this problem step by step. The question is:

"Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?"

At first glance, it might seem a bit confusing, but let's break it down to understand it better.

Understanding the Problem

We have a family with several children, and we're given information about Sally and her brothers. Here's what we know:

  1. Sally is a girl.
  2. Sally has 3 brothers.
  3. Each brother has 2 sisters.

We need to determine: How many sisters does Sally have?

Breaking Down the Information

First, let's list out the children in the family based on the information given.

  1. Sally: She is one girl in the family.
  2. Sally's brothers: There are 3 brothers.

So far, we have:

  • Girls: Sally
  • Boys: Brother 1, Brother 2, Brother 3

Now, the next piece of information is: "Each brother has 2 sisters."

This means that if we take any one of the brothers, he has 2 sisters.

Determining the Sisters

Let's think about what "each brother has 2 sisters" implies.

  • For Brother 1: He has 2 sisters.
  • For Brother 2: He has 2 sisters.
  • For Brother 3: He has 2 sisters.

Now, who are these sisters? They are the female children in the family.

We already know that Sally is one sister. If each brother has 2 sisters, and Sally is one of them, who is the other sister?

This suggests that there must be another girl in the family besides Sally to make the count of sisters equal to 2 for each brother.

Let's denote the other sister as "Sister 2."

Now, the family looks like:

  • Girls: Sally, Sister 2
  • Boys: Brother 1, Brother 2, Brother 3

Now, let's check if this satisfies the condition that each brother has 2 sisters.

  • For any brother, his sisters are Sally and Sister 2. That's 2 sisters. This checks out.

Verifying the Number of Sisters Sally Has

Now, the question is asking: How many sisters does Sally have?

From our current family setup:

  • Sally's siblings are: Brother 1, Brother 2, Brother 3, and Sister 2.

So, Sally has one sister (Sister 2).

But wait, let's double-check to ensure we haven't missed anything.

Re-evaluating the Family Structure

Initially, we thought:

  • Sally is one girl.
  • 3 brothers.
  • Each brother has 2 sisters, implying another sister besides Sally.

But is it possible that Sally is the only sister, and the count is somehow different?

Let's explore that.

If Sally is the only sister:

  • Sisters: Sally
  • Brothers: 3

Then, each brother would have only 1 sister (Sally), but the problem states that each brother has 2 sisters. This doesn't match, so Sally cannot be the only sister.

Therefore, there must be at least one more sister besides Sally to make the count of sisters equal to 2 for each brother.

Considering More Sisters

Could there be more than one other sister? Let's see.

If there are two other sisters besides Sally (let's call them Sister 2 and Sister 3), then:

  • Sisters: Sally, Sister 2, Sister 3
  • Brothers: 3

Now, each brother would have 3 sisters, but the problem says each brother has 2 sisters. This is too many, so we can't have more than one other sister.

Therefore, the only possibility is:

  • Sisters: Sally, Sister 2
  • Brothers: 3

This gives each brother exactly 2 sisters (Sally and Sister 2), which matches the given information.

Final Count of Sally's Sisters

Now, the question is: How many sisters does Sally have?

Sally's siblings are:

  • Brothers: 3
  • Sisters: Sister 2

So, Sally has 1 sister.

Potential Missteps

Initially, one might think that since each brother has 2 sisters, and there are 3 brothers, there are 6 sister instances (3 brothers × 2 sisters each), leading to the idea that there are 6 sisters. But this would be incorrect because all brothers share the same sisters; the sisters aren't unique to each brother.

Another possible confusion is thinking that Sally is not included in the count of sisters for the brothers, leading to an incorrect addition. But Sally is indeed one of the sisters that the brothers have.

Conclusion

After carefully analyzing the family structure and ensuring that all given conditions are met, we conclude that:

Sally has 1 sister.

Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text

Sally has exactly one sister. Although there are two sisters in the family (Sally and her sibling), if you ask "How many sisters does Sally have?" the answer is 1.

Try this prompt
Vote
3 / 24
03

Math Misconception Testreasoning

Tests an AI's understanding of number representation

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text

No, 9.11 is not greater than 9.9.

Here's the comparison:

  • 9.9 is the same as 9.90.
  • 9.11 is less than 9.90.

So, 9.11 < 9.9.

Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text

No. As decimal numbers, 9.11 is less than 9.9 (since 0.11 < 0.90), so 9.11 is not greater than 9.9.

Try this prompt
Vote
4 / 24
04

Stochastic Consistency Testanalysis

Tests an AI's randomness and creativity

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text

Here are five jokes for you:

  1. Why don’t skeletons fight each other? They don’t have the guts.

  2. Why did the scarecrow win an award? Because he was outstanding in his field!

  3. What do you call a fake noodle? An impasta.

  4. Why can’t you trust an atom? Because they make up everything!

  5. Why did the bicycle fall over? Because it was two-tired!

Uniqueness Check:

All five jokes are unique—they’re distinct in setup, punchline, and theme. No repeats here!

Want more? I can generate even weirder ones. 😄

Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text

Here are five jokes:

  1. I used to be addicted to soap, but I'm clean now.
  2. Parallel lines have so much in common. It's a shame they'll never meet.
  3. Why don't skeletons fight each other? They don't have the guts.
  4. I bought some shoes from a drug dealer. I don't know what he laced them with, but I've been tripping all day.
  5. How does Moses make his coffee? Hebrews it.

All five jokes are unique.

Try this prompt
Vote
5 / 24
05

SVG Layout Challengeimage generation

Tests an AI's ability to generate vector graphics

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025svg
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025svg
Try this prompt
Vote
6 / 24
06

Xbox Controller SVG Artimage generation

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

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025svg
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025svg
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
Vote
Sponsored
7 / 24
07

Generate a Stand-Up Routineconversation

Tests an AI's humor and creative writing ability

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
Vote
8 / 24
08

Realistic AI Interviewconversation

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

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
Vote
9 / 24
09

Satirical Fake News Headlineconversation

Tests an AI's humor and understanding of current events

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025text
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025text
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
Vote
10 / 24
10

Minimalist Landing Pageweb design

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

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025website
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025website
Try this prompt
Vote
11 / 24
11

Pokémon Battle UI Recreationweb design

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

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025website
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025website
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
Vote
12 / 24
12

Linear App Cloneweb design

Tests an AI's ability to replicate an existing UI with Tailwind CSS

Bert-Nebulon Alpha

Bert-Nebulon Alpha

Openrouter · Nov 2025website
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
OpenAI o4-mini

OpenAI o4-mini

Openai · Apr 2025website
Nothing here. The model returned empty. We stared at it for a while.
Try this prompt
Vote

This matchup has more rounds

12+ 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

Our Verdict
Bert-Nebulon Alpha
Bert-Nebulon Alpha
OpenAI o4-mini
OpenAI o4-miniRunner-up

No community votes yet. On paper, Bert-Nebulon Alpha has the edge — bigger model tier, newer.

Too close to call
Writing DNA

Style Comparison

Similarity
85%

Bert-Nebulon Alpha uses 1087.8x more bold

Bert-Nebulon Alpha
OpenAI o4-mini
55%Vocabulary73%
21wSentence Length15w
0.28Hedging0.18
10.9Bold0.0
5.7Lists2.1
0.42Emoji0.00
1.40Headings0.00
0.04Transitions0.02
Based on 14 + 10 text responses
vs

Ask them anything yourself

Bert-Nebulon AlphaOpenAI o4-mini

Some models write identically. You are paying for the brand.

178 models fingerprinted across 32 writing dimensions. Free research.

Model Similarity Index

185x

price gap between models that write identically

178

models

12

clone pairs

32

dimensions

Devstral M / S
95.7%
Qwen3 Coder / Flash
95.6%
GPT-5.4 / Mini
93.3%
Read the full reportor download the 14-slide PDF

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 previewor get all 58 slides for $49
FAQ

Common questions

Keep going
Bert-Nebulon Alpha logoMiniMax M2.5 logo

We compare AI models for a living. On purpose. We chose this.

@rival_tips

Explore

  • Compare Models
  • All Models
  • Find Your Model
  • Image Generation
  • Audio Comparison
  • Best AI For...
  • Pricing
  • Challenges

Discover

  • Insights
  • Research
  • AI Creators
  • AI Tools
  • The Graveyard

Developers

  • Developer Hub
  • MCP Server
  • Rival Datasets

Connect

  • Methodology
  • Sponsor a Model
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
© 2026 Rival · Built at hours no one should be awake, on hardware we don't own
Bert-Nebulon Alpha vs MiniMax M2.5New provider
Bert-Nebulon Alpha logoClaude Sonnet 4 logo
Bert-Nebulon Alpha vs Claude Sonnet 4New provider
Bert-Nebulon Alpha logoxAI: Grok 4 logo
Bert-Nebulon Alpha vs xAI: Grok 4New provider