Model Comparison
Claude Sonnet 5 vs GPT-5.6 Luna
Too close to call: the best configurations, Claude Sonnet 5 (max effort) and GPT-5.6 Luna (ultra), are 47 Elo apart, and their 95% ranges overlap. Among 78 models, each ranked by its best configuration, Claude Sonnet 5 is #23 and GPT-5.6 Luna is #24. Cost per script: $0.696 for Claude Sonnet 5 (max effort) and $0.026 for GPT-5.6 Luna (ultra).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickClaude Sonnet 5
Claude Sonnet 5 (max effort)
Pick Claude Sonnet 5 (max effort) when the first draft has to sound like me and land on length, at $0.696 a script.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) for the bulk of the work, since the board can't separate it from Sonnet's best and it costs $0.026 a script.
About 27 times the price buys Claude Sonnet 5 a 47 Elo lead that the board can't confirm. Claude Sonnet 5 is the #23 model of 78 and GPT-5.6 Luna the #24 model, each ranked by its best setting. The 95% ranges of Claude Sonnet 5 (max effort) and GPT-5.6 Luna (ultra) overlap. Luna costs $0.026 a script and Sonnet $0.696, and Sonnet takes 12 minutes where Luna needs about three. The thinking levels don't help Sonnet's case: Luna at ultra costs less than Claude Sonnet 5 (high) and leads it by 160 Elo with separate ranges. Luna's own cheap setting is no bargain either. GPT-5.6 Luna (medium) drops far below ultra, and the board can't separate it from Sonnet at high, so I'd only run these two at their top setting. They do write differently. Sonnet sounds a little more like me, two to three points ahead on voice, continuity and YouTube structure, and it holds the length better. Luna opens stronger, about five points up on hooks, and packs in more substance. For most scripts I'd take Luna at ultra and fix the voice myself.
Disclosure: Claude Sonnet 5 and GPT-5.6 Luna each come from the same lab as one of the judges (Claude Opus 5.5 and GPT-6.1 Sol). Neither is 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 Claude Sonnet 5 and GPT-5.6 Luna, 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 | Configuration Rank |
|---|---|---|---|---|---|---|
| Claude Sonnet 5 (max effort) | 1859 | 1812 to 1904 | 79.2 | $0.696 | 12.0 min | #45 |
| GPT-5.6 Luna (ultra) | 1812 | 1768 to 1858 | 78.8 | $0.026 | 3.1 min | #49 |
| Claude Sonnet 5 (high) | 1652 | 1602 to 1703 | 76.6 | $0.121 | 1.9 min | #58 |
| GPT-5.6 Luna (medium) | 1609 | 1572 to 1647 | 76.7 | $0.0065 | 0.5 min | #66 |
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.
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. Claude Sonnet 5 (max effort) at Elo 1859 (range 1812 to 1904) and GPT-5.6 Luna (ultra) at Elo 1812 (range 1768 to 1858) have overlapping 95% ranges, so the board cannot separate the two best configurations.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Claude Sonnet 5 (high) at Elo 1652 and $0.121 per script leads GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script by 43 Elo. Their 95% ranges overlap, so the board cannot separate them.
- Cheapest Configuration Overlapping the Top One. GPT-5.6 Luna (ultra), at $0.026 per script, is the cheapest configuration whose 95% range overlaps that of Claude Sonnet 5 (max effort), at $0.696 per script: 1768 to 1858 against 1812 to 1904, so the board cannot separate them. Claude Sonnet 5 (max effort) costs about 27 times as much per script.
- Cheapest Claude Sonnet 5 Configuration Above GPT-5.6 Luna's Best. The cheapest Claude Sonnet 5 configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1812 and $0.026 per script, is Claude Sonnet 5 (max effort), at Elo 1859 and $0.696 per script. Their 95% ranges overlap, so the board cannot separate them. It costs about 27 times as much per script.
- Lowest to Highest Thinking Level. Claude Sonnet 5 moves +207 Elo from high to max effort, at about 5.8 times the cost per script. GPT-5.6 Luna moves +203 Elo from medium to ultra, at about 4 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
Claude Sonnet 5 (max effort) scores higher on five of the nine metrics and GPT-5.6 Luna (ultra) on four. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Claude Sonnet 5 (max effort) ahead, with a 3.1-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Claude Sonnet 5 (max effort) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 2.39 | 2.07 |
| Lowest script score | 75.7 Script 4 | 76.0 Script 7 |
| Highest script score | 81.5 Script 9 | 80.8 Script 9 |
| Range across scripts | 5.8 | 4.8 |
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 Claude Sonnet 5 (max effort) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | Claude Sonnet 5 (max effort) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 77.4 | 78.5 | -1.1 |
| Script 2 news-analysis / skeptical explainer | 78.9 | 80.3 | -1.4 |
| Script 3 personal roadmap / opinion | 78.1 | 79.7 | -1.6 |
| Script 4 short explainer | 75.7 | 77.4 | -1.7 |
| Script 5 news-analysis / opinion explainer | 80.9 | 79.7 | +1.2 |
| Script 6 founder announcement / personal origin story | 81.1 | 80.6 | +0.5 |
| Script 7 personal technical walkthrough / agentic workflow case study | 81.2 | 76.0 | +5.2 |
| Script 8 product release announcement / personal observation | 79.3 | 78.4 | +0.9 |
| Script 9 career guide / hiring analysis | 81.5 | 80.8 | +0.7 |
| Script 10 engineering process walkthrough / presentation adaptation | 78.0 | 76.9 | +1.1 |
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