GPT-5.6 Sol (ultra) vs Grok 4.7
Should you write with GPT-5.6 Sol (ultra) or Grok 4.7? On this page the only thing that changes is the model. Both wrote their own version of the scripts behind 10 of my What's AI videos, five drafts per script, and four judges (three LLM judges from three model families plus Jev, a typed judge from TypeSafe) scored every draft blind, with my finished script as the reference. They tie on the overall score at 87.6, and GPT-5.6 Sol (ultra) ranks higher on Elo, #31 to #32. Their per-model Elo intervals overlap on this board. Heads-up: GPT-5.6 Sol (ultra) shares its model line with one of the four judges. The panel spans three LLM families plus Jev, a typed judge from TypeSafe, so no model here is scored by its own family alone (how the panel works).
The verdict
A near tie that splits by what you care about. GPT-5.6 Sol (ultra) is #31 and Grok 4.7 is #32, their intervals overlap, and their overall scores are less than a point apart. Grok sounds more like a person: it leads on Tone & Voice Match by about five points and on Hook Strength and Continuity & Emotion by two to three. GPT-5.6 Sol wins Length Adherence by about twenty points and slightly edges Visual Cue Quality. Grok costs a bit more, about twenty-seven cents against twenty-five, and takes more than twice as long.
Pick GPT-5.6 Sol (ultra) for scripts that hit their length and come back fast.
Pick Grok 4.7 for a stronger voice and hooks.
How to read these numbers
Overall vs Elo. Overall is the weighted rubric score. Elo compares each model's five-draft average with every other model's, script by script, and counts gaps inside run-to-run noise as draws, so it rewards winning often and can disagree with overall.
Reading the Elo intervals. Each 95% range comes from resampling every model's recorded run scores on each task and re-ranking. Comparing these separate ranges does not test the Elo gap between two models: far apart is strong evidence, and overlap isn't a tie. The tasks stay fixed, so the ranges say nothing about new tasks (the long version).
Metric by metric: where the gap comes from
Blue is GPT-5.6 Sol (ultra), orange is Grok 4.7, and the solid bar takes the metric. The weight under each name is how much it counts toward the overall. If you care about one thing, say voice or length, go straight to that row.
Cost, speed, and consistency
Quality is half the decision. The other half is what each script costs you, how long you wait, and how often you get a bad draft. They cost about the same per script.
| GPT-5.6 Sol (ultra) | Grok 4.7 | |
|---|---|---|
| Overall / 100 | 87.6 | 87.6 |
| Writing Elo | 2148 | 2143 |
| Score spread across drafts (± overall std) | 1.290 | 2.490 |
| Cost per script (USD) | 0.249 | 0.267 |
| Avg time per script (min) | 3.3 | 7.7 |
| Open weights | No | No |
Green wins the row, and for spread, cost and time, lower wins. Cost is one script at recorded list prices, uncached and without judging, so your real bill will differ. Spread is how much the overall score moves across a model's drafts, and time is the average time to get one accepted script, retries included.
Want the script-by-script detail? Full scorecards: GPT-5.6 Sol (ultra) · Grok 4.7. The whole scoring pipeline is on the methodology page.
← All comparisons