Grok 4.7 (high) vs GPT-5.6 Sol (ultra)
Should you write with Grok 4.7 (high) or GPT-5.6 Sol (ultra)? 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 Grok 4.7 (high) ranks higher on Elo, #26 to #31. 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
These two are too close to call on this board: #31 and #26, about eighteen Elo points apart, with heavily overlapping ranges. So you're picking on style. I lean GPT-5.6 Sol (ultra) because it's predictable. Grok 4.7 (high) trails by almost eighteen points on Length Adherence, tends to run long, and swings a lot from run to run. GPT is also faster, about three minutes per script against close to nine. Grok's strengths sit on the voice side, though: it wins Tone & Voice Match, the heaviest-weighted metric in the rubric, and Continuity & Emotion, but it costs about a quarter more, $0.311 against $0.249. If you trim scripts anyway, Grok is the stronger pick on voice.
Pick GPT-5.6 Sol (ultra) when you need predictable length and a faster turnaround.
Pick Grok 4.7 (high) when voice and flow matter most and you don't mind trimming overlong drafts.
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 Grok 4.7 (high), orange is GPT-5.6 Sol (ultra), 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. Grok 4.7 (high) costs about 1.2x as much per script as GPT-5.6 Sol (ultra).
| Grok 4.7 (high) | GPT-5.6 Sol (ultra) | |
|---|---|---|
| Overall / 100 | 87.6 | 87.6 |
| Writing Elo | 2166 | 2148 |
| Score spread across drafts (± overall std) | 2.430 | 1.290 |
| Cost per script (USD) | 0.311 | 0.249 |
| Avg time per script (min) | 8.7 | 3.3 |
| 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: Grok 4.7 (high) · GPT-5.6 Sol (ultra). The whole scoring pipeline is on the methodology page.
← All comparisons