Kimi K2 Thinking vs Gemini 3.1 Pro Preview
Compare Kimi K2 Thinking by Moonshot AI against Gemini 3.1 Pro Preview by Google AI, context windows of 262K vs 1.0M, tested across 35 shared challenges. Updated February 2026.
Compare Kimi K2 Thinking by Moonshot AI against Gemini 3.1 Pro Preview by Google AI, context windows of 262K vs 1.0M, tested across 35 shared challenges. Updated February 2026.
30 challenges
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 can use a well-established heuristic in deep learning for estimating the compute cost of training Transformer-based large language models.
The estimated total compute is roughly $3.15 \times 10^{23}$ FLOPs.
Here is the step-by-step reasoning used to arrive at this number:
To calculate the compute required, we need to know two fundamental numbers about the model:
In language model training, the total compute ($C$) is heavily dominated by the matrix multiplications in the dense layers. OpenAI's scaling laws provide a standard, highly accurate approximation formula for this: $C \approx 6 \times N \times D$
Why the multiplier of 6?
(Note: This formula slightly underestimates by ignoring the quadratic cost of attention and optimizer state updates, but at the 175B scale, the dense feed-forward matrices dominate the compute so heavily that $6ND$ is considered the gold-standard approximation).
Now we simply plug the numbers into our formula:
First, multiply $N$ and $D$:
Next, multiply by 6 (for the forward and backward passes):
Does $3.15 \times 10^{23}$ FLOPs make sense in the real world? When GPT-3 was trained (around late 2019/early 2020), Nvidia V100 GPUs were the standard.
Given that training runs of this size typically take a few weeks on a few thousand GPUs (factoring in downtime, checkpointing, and slightly smaller clusters), this math aligns perfectly with historical reality.
Conclusion: The total compute required to train GPT-3 was approximately $3.15 \times 10^{23}$ FLOPs.
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Tests an AI's randomness and creativity
Here are 5 jokes:
How many are unique? Within this list, all 5 are unique from one another (there are no duplicates). However, if you mean "unique" as in completely original to the world, the answer is 0—these are all classic, well-known "dad jokes" that have been around for a long time!
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
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 generate a complete, working landing page
Recreate an interactive, classic Mario level in a single HTML file.
Tests an AI's ability to create smooth web animations
Tests an AI's ability to engage in philosophical discourse about AI rights
Tests an AI's ability to make reasonable predictions about technology
Generate SVG art of a randomly chosen animal in a setting of its choosing.