Kimi K3 (thinking) vs GPT-5.6 Sol (high)
Should you write with Kimi K3 (thinking) or GPT-5.6 Sol (high)? 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 three judges from three model families scored every draft blind, with my finished script as the reference. GPT-5.6 Sol (high) leads overall, 87.6 to 87.2. Their per-model Elo intervals overlap on this board. Heads-up: GPT-5.6 Sol (high) shares its model line with one of the three judges. The panel spans three model families, so no model here is scored by its own family alone (how the panel works).
The verdict
A close one, and I'd lean GPT-5.6 Sol (high) by a nose. The ranks are #33 and #41, the overall scores 0.4 apart, and the Elo ranges overlap, so the board can't call it. They win different things. GPT-5.6 Sol (high) is tidier: better visual cues, fewer slop patterns, closer to the target length. Kimi K3 (thinking) scores closer to my reference voice, with the stronger hook and a small edge on Tone & Voice Match. It's also cheaper, $0.095 per script against $0.155, with open weights. So if voice and cost matter more than polish, Kimi is a fine call. Also worth a look: plain Kimi K3, without thinking, ranks well above both.
Pick GPT-5.6 Sol (high) for tidier scripts with better cues, less slop and tighter length.
Pick Kimi K3 (thinking) for a stronger hook and voice at a lower price, with open weights.
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. My own scripts score 90.9 on the same rubric, not a literal 100. Right now 2 of 167 ranked configurations reach it. A model above that line writes at that level on this rubric. That's not the same as beating my script line for line.
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 Kimi K3 (thinking), orange is GPT-5.6 Sol (high), and the solid bar takes the metric. The weight under each name is how much it counts toward the overall. Weighted by how much each metric counts, Length Adherence does the most to put GPT-5.6 Sol (high) ahead: it leads there by 3.0 points. 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. The lead has a price: GPT-5.6 Sol (high) costs about 1.6x as much per script as Kimi K3 (thinking).
| Kimi K3 (thinking) | GPT-5.6 Sol (high) | |
|---|---|---|
| Overall / 100 | 87.2 | 87.6 |
| Writing Elo | 2098 | 2134 |
| Score spread across drafts (± overall std) | 1.550 | 1.330 |
| Cost per script (USD) | 0.095 | 0.155 |
| Avg time per script (min) | 1.2 | 1.4 |
| Open weights | Yes | 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: Kimi K3 (thinking) · GPT-5.6 Sol (high). The whole scoring pipeline is on the methodology page.
← All comparisons