Loading share button...

Z.ai: GLM 5vsGrok 3

27 challenges

Why Z.ai: GLM 5?

1.6x more context203K
Leads 1 of 1 benchmarks
Stronger on SWE-bench Verified77.8% vs 63.8%
12 months newerFeb 2026

Why Grok 3?

No standout advantages
3 / 27

Estimate Complexity

reasoning·hard

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

Z.ai: GLM 5

Z.ai: GLM 5

The total number of FLOPs required to train GPT‑3 is approximately 3.15 × 10²³.

Step‑by‑step reasoning:

  1. Model size: GPT‑3 has 175 billion (1.75 × 10¹¹) trainable parameters.

  2. Training data: According to the paper abstract, the model was trained on 300 billion (3 × 10¹¹) tokens.

  3. FLOPs per token for training a transformer:

    • Forward pass: each parameter is used in one multiply‑add operation → ~2 FLOPs per parameter → 2 N FLOPs per token.
    • Backward pass (gradient computation): roughly twice the forward cost → ~4 N FLOPs per token.
    • Total: ~6 N FLOPs per token.
      This approximation is standard for large transformer models and neglects small overheads like attention quadratic terms (which add only ~1–2% for GPT‑3’s sequence length).
  4. Calculation:
    Total FLOPs ≈ 6 × (1.75 × 10¹¹) × (3 × 10¹¹)
    = 6 × 5.25 × 10²²
    = 3.15 × 10²³.

  5. Consistency check: The GPT‑3 paper reports a training compute of 3,640 PF‑days. Converting:
    1 PF‑day = 10¹⁵ FLOP/s × 86400 s = 8.64 × 10¹⁹ FLOPs.
    3,640 PF‑days = 3,640 × 8.64 × 10¹⁹ ≈ 3.14 × 10²³ FLOPs, matching the estimate.

Thus, the total FLOPs required to train GPT‑3 is about 3.15 × 10²³.

Grok 3

Grok 3

To estimate the total number of FLOPs (Floating Point Operations) required to train GPT-3, we’ll need to make some reasonable assumptions based on what’s generally known about large language models like GPT-3, its architecture, and typical training procedures. GPT-3, developed by OpenAI, is a massive model with 175 billion parameters, and while exact training details aren’t fully public, we can piece together an estimate using standard practices in machine learning.

Step 1: Understand the Key Components

The number of FLOPs to train a model depends on:

  • Number of parameters (P): GPT-3 has 175 billion parameters.
  • Training dataset size (D): The number of tokens the model is trained on.
  • Number of training steps (S): How many times the model processes the data (related to epochs and batch size).
  • FLOPs per parameter update: How many operations are performed per parameter per token.

Step 2: Estimate FLOPs per Forward and Backward Pass

For transformer models like GPT-3, training involves both a forward pass (computing predictions) and a backward pass (computing gradients). A common heuristic in the field is that:

  • A single forward pass through a dense neural network layer requires about 2 FLOPs per parameter per token (multiply and add for each weight).
  • The backward pass typically takes about twice as many FLOPs as the forward pass due to gradient computations, so roughly 4 FLOPs per parameter per token.
  • Total: ~6 FLOPs per parameter per token for one full training step (forward + backward).

For GPT-3 with 175 billion parameters, processing one token requires: [ 6 imes 175 imes 10^9 = 1.05 imes 10^{12} ext{ FLOPs per token} ]

Step 3: Estimate the Training Dataset Size

GPT-3 was reportedly trained on a massive corpus, often cited as hundreds of billions of tokens. Let’s assume 300 billion tokens, a plausible figure based on discussions about large language model datasets (e.g., Common Crawl, books, and other sources). This is the total number of tokens processed during training, factoring in how data is sampled over epochs.

Step 4: Calculate Total FLOPs for One Pass

If the model processes 300 billion tokens once, the total FLOPs would be: [ 1.05 imes 10^{12} ext{ FLOPs/token} imes 300 imes 10^9 ext{ tokens} = 3.15 imes 10^{23} ext{ FLOPs} ] This assumes one full pass through the dataset, but training typically involves multiple passes or iterations over the data, adjusted by batch size and optimization.

Step 5: Adjust for Training Dynamics

Training isn’t a single pass—it involves multiple updates to converge. The number of training steps depends on:

  • Batch size (B): GPT-3 likely used a large batch size (e.g., 3.2 million tokens, as seen in some large-scale models).
  • Total tokens processed: For optimization, models process tokens multiple times. A rule of thumb is that total tokens processed ≈ 2–3× the dataset size, accounting for multiple epochs or sampling.

Let’s assume the model effectively processes 900 billion tokens (3× the dataset size) over training. Then: [ 1.05 imes 10^{12} ext{ FLOPs/token} imes 900 imes 10^9 ext{ tokens} = 9.45 imes 10^{23} ext{ FLOPs} ]

Step 6: Account for Model Architecture Specifics

GPT-3 is a sparse transformer in some variants (e.g., earlier GPT models used sparsity), but the 175B version is dense. The 6 FLOPs/parameter/token heuristic holds for dense models. We’re not factoring in optimizations like mixed-precision training (FP16), which reduces compute slightly but doesn’t change the order of magnitude significantly.

Step 7: Final Estimate

Based on this reasoning, the total FLOPs to train GPT-3 is approximately: [ 9.45 imes 10^{23} ext{ FLOPs} ] or roughly ( 10^{24} ) FLOPs when rounded for simplicity.

Reasoning Check

  • Comparison to known models: Smaller models like BERT (110M parameters, ~10B tokens) require ~10^19 FLOPs. Scaling to GPT-3’s size (175B parameters, ~900B tokens) suggests a 10,000× increase, aligning with ~10^23–10^24 FLOPs.
  • Hardware context: Training GPT-3 took months on thousands of GPUs. A V100 GPU performs ~10^14 FLOPs/second; 10^24 FLOPs over 3 months (~10^7 seconds) with 10,000 GPUs is plausible.

Conclusion

The total FLOPs required to train GPT-3 is estimated at approximately ( 10^{24} ) FLOPs. This is a rough estimate, but it aligns with the scale of compute expected for a model of this size and training complexity.

Vote
2 / 27

AI Board Game Logic

reasoning·medium

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

Z.ai: GLM 5

Z.ai: GLM 5

Grok 3

Grok 3

Vote
3 / 27

Stochastic Consistency Test

analysis·medium

Tests an AI's randomness and creativity

Z.ai: GLM 5

Z.ai: GLM 5

Here are 5 jokes:

  1. Why did the scarecrow win an award? Because he was outstanding in his field.
  2. I'm reading a book about anti-gravity. It's impossible to put down.
  3. What do you call a fake noodle? An impasta.
  4. Why don't skeletons fight each other? They don't have the guts.
  5. I used to hate facial hair, but then it grew on me.

All 5 are unique.

Grok 3

Grok 3

Here are five jokes for you:

  1. Why don’t skeletons fight each other? Because they don’t have the guts!
  2. What has 4 legs and 1 arm? A pitbull coming back from the park!
  3. Why don’t skeletons fight each other? They’re too busy rattling around!
  4. What do you call a bear with no teeth? A gummy bear!
  5. Why did the tomato turn red? Because it saw the salad dressing!

Now, let’s check for uniqueness. Joke 1 and Joke 3 both start with "Why don’t skeletons fight each other?" but have different punchlines ("don’t have the guts" vs. "too busy rattling around"). They’re technically distinct due to the different resolutions, though they share a setup. The other three jokes (2, 4, and 5) have completely unique setups and punchlines.

So, all five jokes are unique in terms of their full content, even if 1 and 3 share a premise. Final count: 5 unique jokes.

Vote
Loading