Notes: We think that RL relative to pre-compute is between our estimate for o3 (10% of pre-training) and the 100% implied by this slide in the launch ( https://archive.is/f0vJU ). Assuming the same pre-training as Grok 3 (also implied by that slide, and much more consistent) and that Grok 3 used a tenth as much RL, we get: 2 * (grok3/1.1) in the high case (rl is 10% of grok 3, so grok3/1.1 is grok3 precompute, and in this case twice that is grok 4) 1.1 * (grok3/1.01) in the low case The geometric mean is (rounded to one sig fig): 5e26