Compare Claude Opus 4.6 by Anthropic against Qwen: Qwen3.5 122B A10B by Qwen, context windows of 1.0M vs 262K, tested across 52 shared challenges. Updated February 2026.
47 fights queued
Tests an AI's ability to make educated estimates based on technical knowledge
To estimate the total number of FLOPs (Floating Point Operations) required to train GPT-3, we need to rely on the known architectural hyperparameters of the model and the standard computational scaling laws established in deep learning literature (specifically from the "Scaling Laws for Neural Language Models" paper by Kaplan et al., which preceded and informed the GPT-3 work).
Here is the step-by-step reasoning and calculation.
From the "Language Models are Few-Shot Learners" paper (Brown et al., 2020), we can recall the specific configuration of the largest GPT-3 model:
Note: While the context length (2048 tokens) affects memory bandwidth and sequence processing, the total training FLOPs are primarily driven by the number of parameters and the total number of tokens processed.
To estimate the computational cost, we use the standard approximation for Transformer training derived in scaling law research.
Therefore, the total training compute ($C$) is estimated as: $$C \approx 6 \times N \times D$$
Note: This estimate assumes standard optimization (like Adam) overhead is absorbed into this factor or is negligible compared to the model computation itself, which aligns with the "6ND" rule of thumb widely cited in AI infrastructure analysis.
Now, we substitute the values from Step 1 into the formula from Step 2.
$$C = 6 \times (175 \times 10^9) \times (300 \times 10^9)$$
First, multiply the coefficients: $$6 \times 175 \times 300$$ $$6 \times 175 = 1,050$$ $$1,050 \times 300 = 315,000$$
Next, handle the powers of 10: $$10^9 \times 10^9 = 10^{18}$$
Combine them: $$C = 315,000 \times 10^{18}$$
Convert to scientific notation: $$C = 3.15 \times 10^5 \times 10^{18}$$ $$C = 3.15 \times 10^{23} \text{ FLOPs}$$
In the original GPT-3 paper, the authors explicitly state in their Appendix that the training compute was approximately $3.14 \times 10^{23}$ FLOPs.
My estimation of $3.15 \times 10^{23}$ FLOPs is extremely close to the reported figure. The minor difference (0.3%) arises from minor variations in how specific operations (like embedding lookups or optimizer state updates) are counted, but the $6ND$ heuristic is highly accurate for this purpose.
The total number of FLOPs required to train GPT-3 is approximately:
$3.15 \times 10^{23}$ FLOPs
Tests an AI's ability to understand game rules and strategy
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Sally has 1 sister.
Here is the breakdown:
Tests an AI's randomness and creativity
Here are 5 jokes:
How many are unique? All 5 are unique. Each joke is distinct from the others.
Tests an AI's ability to generate vector graphics
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's humor and creative writing ability
Tests an AI's ability to simulate personalities and predict future trends
Tests an AI's humor and understanding of current events
Tests an AI's ability to write in distinct character voices
Tests an AI's ability to generate a complete, working landing page
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
35+ challenges you’re sleeping on
5 free credits on signup
By continuing, you agree to Rival's Terms of Service and Privacy Policy
