Model Comparison
GPT-6 Sol vs Kimi K3.1 Pro
GPT-6 Sol (max) leads Kimi K3.1 Pro (max) by 148 Elo, and their 95% ranges sit 66 Elo apart. Among 83 models, each ranked by its best configuration, GPT-6 Sol is #4 and Kimi K3.1 Pro is #7. Cost per script: $0.126 for GPT-6 Sol (max) and $0.251 for Kimi K3.1 Pro (max).
Last updated , from board data generated at 22:06 UTC.
Picks and Verdict
PickGPT-6 Sol
GPT-6 Sol (max)
Pick GPT-6 Sol (max) for the final script, since it leads Kimi K3.1 Pro (max) by 148 Elo with separate ranges at about half the price, $0.126 a script.
PickKimi K3.1 Pro
Kimi K3.1 Pro (max)
Pick Kimi K3.1 Pro (max) when visual cues and length carry the video, since it leads GPT-6 Sol (max) there by 3.4 and 2.5 points, at $0.251 a script.
GPT-6 Sol beats Kimi K3.1 Pro on rating, price and speed. GPT-6 Sol (max) sits 148 Elo above Kimi K3.1 Pro (max) with separate 95% ranges and wins eight of the ten scripts, for $0.126 a script against $0.251 and two and a half minutes against 5.5. By best configuration, that's the #4 model of 83 against the #7 model. Sol's medium setting makes it harder still for Kimi. GPT-6 Sol (medium) sits 1 Elo below Kimi with overlapping ranges, so the board can't separate them, and it costs $0.056, under a quarter of Kimi's price, back in under a minute. Sol gains 149 Elo from medium to max for about 2.3 times the cost, an easy yes at these prices. The two are level on substance and hooks. Sol is about three points ahead on tone and has the cleaner Slop Score. Kimi's visual cues are about three and a half points better, and it lands closer to the target length. Unless visual cues are what your drafts keep missing, I'd run Sol at max and keep medium for volume.
Disclosure: GPT-6 Sol comes from the same lab as one of the four judges, GPT-6.1 Sol. The other three sit outside its lab, so it is never scored by its own lab alone (how the panel works). The judge analysis measures how much each judge favors its own lab.
How to Read the Writing Score, Writing Elo and 95% Ranges
Writing Score and Writing Elo. The Writing Score (0 to 100) is the weighted average of the nine metric scores: seven from the judges, Length Adherence from code and the Slop Score half from each. The Writing Elo is a rating from pairwise comparisons: on each script, each configuration's average across its drafts is compared with every other configuration's, and gaps within the draft-to-draft variation count as draws. Elo rewards winning often, so the two can put configurations in a different order.
Elo ranges. Each 95% range shows how far a configuration's Elo could move if the drafts had come out slightly differently. It comes from resampling every configuration's recorded draft scores on each reference script and ranking again. Comparing two separate ranges does not test the Elo gap between them: ranges far apart are strong evidence for the order, and overlapping ranges do not mean a tie. The reference scripts stay fixed, so the ranges say nothing about new scripts. The methodology page has the full description.
All Thinking Levels of Both Models
Every ranked configuration of GPT-6 Sol and Kimi K3.1 Pro, scored on the same 10 scripts by the same four judges.
- Each row is one configuration: the model at one thinking level. The dot is its Writing Elo, a rating from pairwise comparisons of the scores on each script, and the bar is its 95% range: how far that Elo could move if the drafts had come out slightly differently.
- When two bars overlap, the board cannot order those two configurations. Bars far apart are strong evidence for the order.
- The table under the chart lists the same configurations in the same order and adds the Writing Score (the 0 to 100 consensus of the judges and code), cost, time and configuration rank (the place among all configurations on the board).
Shaded rows are the configurations chosen for the metric comparison below.
| Configuration | Writing Elo | 95% Range | Writing Score | Cost / Script | Time / Script | Reasoning Tokens | Configuration Rank |
|---|---|---|---|---|---|---|---|
| GPT-6 Sol (max) | 2353 | 2312 to 2394 | 83.5 | $0.126 | 2.5 min | N/A | #8 |
| Kimi K3.1 Pro (max) | 2205 | 2166 to 2246 | 82.5 | $0.251 | 5.5 min | 19,487 | #14 |
| GPT-6 Sol (medium) | 2204 | 2160 to 2247 | 82.5 | $0.056 | 0.8 min | N/A | #15 |
Cost is one script at the API list price of the route used, uncached and without judging. Time is the average for one accepted script, retries included. N/A under Reasoning Tokens means the board has no separate reasoning count for that route.
Computed Findings Across Thinking Levels
Each finding is computed from the configurations above. Where two 95% ranges overlap, the board cannot order those two configurations.
- Best Configurations Head to Head. GPT-6 Sol (max) leads Kimi K3.1 Pro (max) by 148 Elo, and their 95% ranges do not overlap (2312 to 2394 against 2166 to 2246), which is strong evidence for that order.
- Same Level Name, Side by Side. At max, the one level name both models use, GPT-6 Sol has the higher Writing Elo: 2353 against 2205. Their 95% ranges do not overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest GPT-6 Sol Configuration Above Kimi K3.1 Pro's Best. The cheapest GPT-6 Sol configuration with a higher Writing Elo than Kimi K3.1 Pro (max), at Elo 2205 and $0.251 per script, is GPT-6 Sol (max), at Elo 2353 and $0.126 per script. It costs less than the configuration it beats.
- Lowest to Highest Thinking Level. GPT-6 Sol moves +149 Elo from medium to max, at about 2.3 times the cost per script.
Two Chosen Configurations Compared
Pick one configuration of each model to compare their metric scores, consistency across drafts and per-script scores. Each menu starts on the model's best configuration.
Scores by Metric
GPT-6 Sol (max) scores higher on five of the nine metrics and Kimi K3.1 Pro (max) on four. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put GPT-6 Sol (max) ahead, with a 3.2-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| GPT-6 Sol (max) | Kimi K3.1 Pro (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.27 | 1.65 |
| Lowest script score | 82.0 Script 10 | 80.4 Script 7 |
| Highest script score | 85.3 Script 9 | 85.5 Script 9 |
| Range across scripts | 3.3 | 5.1 |
Spread is how much the Writing Score moves between a configuration's drafts, and lower is steadier. Green marks the better number in each row.
Scores by Script
Writing Score on each reference script. Gap is GPT-6 Sol (max) minus Kimi K3.1 Pro (max), and the higher score is in bold.
| Script | GPT-6 Sol (max) | Kimi K3.1 Pro (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 83.0 | 81.3 | +1.7 |
| Script 2 news-analysis / skeptical explainer | 83.7 | 83.2 | +0.5 |
| Script 3 personal roadmap / opinion | 84.3 | 81.9 | +2.4 |
| Script 4 short explainer | 83.3 | 82.0 | +1.3 |
| Script 5 news-analysis / opinion explainer | 83.4 | 84.2 | -0.8 |
| Script 6 founder announcement / personal origin story | 84.8 | 83.0 | +1.8 |
| Script 7 personal technical walkthrough / agentic workflow case study | 82.7 | 80.4 | +2.3 |
| Script 8 product release announcement / personal observation | 82.8 | 82.1 | +0.7 |
| Script 9 career guide / hiring analysis | 85.3 | 85.5 | -0.2 |
| Script 10 engineering process walkthrough / presentation adaptation | 82.0 | 81.3 | +0.7 |
Scorecards and Thinking Pages
Each configuration name in the table above opens its own scorecard.
Compare With Another Model
Pick a second model. A pair with its own written match-up opens that page, and any other pair opens in the comparison tool.
Nearby Match-Ups by Best Writing Elo
Every configuration wrote five drafts for each of the same 10 briefs, from the same prompt. Generation was closed-book, with the prompt as the only source and no web search or other tools. Each judge scores every draft once: Claude Opus 5.5 at medium effort through the Claude Code subscription, GPT-6.1 Sol at medium reasoning through the Codex CLI, GLM 5.3 Flash through OpenRouter, and Jev 1.13, a typed judge from TypeSafe that answers each metric as a multiple-choice question. The channel's finished script is their reference for the voice, and it gets no score on the board itself.
← All comparisons