Model Comparison
Muse Wonder vs GPT-5.6 Luna
Muse Wonder (max) leads GPT-5.6 Luna (ultra) by 195 Elo, and their 95% ranges sit 102 Elo apart. Among 80 models, each ranked by its best configuration, Muse Wonder is #16 and GPT-5.6 Luna is #25. Cost per script: $0.309 for Muse Wonder (max) and $0.026 for GPT-5.6 Luna (ultra).
Last updated , from board data generated at 20:08 UTC.
Picks and Verdict
PickMuse Wonder
Muse Wonder (max)
Pick Muse Wonder (max) when tone matters most, since it leads Luna's best by 4.8 points on Tone & Voice Match and by 195 Elo with separate ranges, at $0.309 a script.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) for cheap drafts at $0.026 a script, since it beats both of Muse's lower settings with separate ranges.
Muse Wonder writes the better script here, and GPT-5.6 Luna costs about a twelfth as much. Muse Wonder (max) leads GPT-5.6 Luna (ultra) by 195 Elo with 95% ranges 102 Elo apart and wins nine of the ten scripts. That makes Muse the #16 model of 80 and Luna the #25 model. Muse costs $0.309 a script against $0.026 but is faster, 2.0 minutes to Luna's 3.1. The gap is in how the script reads: Muse is 4.8 points up on Tone & Voice Match, the metric with the most weight, and 4.3 on continuity. Luna lands the length 9.3 points better. Below Muse's max, Luna takes over. Luna at ultra beats Muse Wonder (high) by 146 Elo with separate ranges for less than a fifth of its price, and Muse Wonder (adaptive), where the model picks its own level, by 206. Even GPT-5.6 Luna (medium), at $0.0065 and half a minute, can't be separated from either of those two Muse settings. So Muse is worth running at max or not at all. I'd pay for it on the scripts I publish and keep Luna at ultra for cheap drafts.
Disclosure: GPT-5.6 Luna 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 Muse Wonder 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 | Reasoning Tokens | Configuration Rank |
|---|---|---|---|---|---|---|---|
| Muse Wonder (max) | 2005 | 1959 to 2044 | 80.6 | $0.309 | 2.0 min | 9,601 | #31 |
| GPT-5.6 Luna (ultra) | 1810 | 1754 to 1857 | 78.8 | $0.026 | 3.1 min | N/A | #50 |
| Muse Wonder (high) | 1664 | 1600 to 1724 | 76.7 | $0.149 | 0.9 min | 1,385 | #58 |
| GPT-5.6 Luna (medium) | 1609 | 1575 to 1644 | 76.7 | $0.0065 | 0.5 min | N/A | #68 |
| Muse Wonder (adaptive) | 1604 | 1550 to 1661 | 76.2 | $0.139 | 0.8 min | 766 | #70 |
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. Muse Wonder (max) leads GPT-5.6 Luna (ultra) by 195 Elo, and their 95% ranges do not overlap (1959 to 2044 against 1754 to 1857), which is strong evidence for that order.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Muse Wonder (high) at Elo 1664 and $0.149 per script leads GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script by 55 Elo. Their 95% ranges overlap, so the board cannot separate them.
- Cheapest Muse Wonder Configuration Above GPT-5.6 Luna's Best. The cheapest Muse Wonder configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1810 and $0.026 per script, is Muse Wonder (max), at Elo 2005 and $0.309 per script. It costs about 12 times as much per script.
- Lowest to Highest Thinking Level. Muse Wonder moves +341 Elo from high to max, at about 2.1 times the cost per script. GPT-5.6 Luna moves +201 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
Muse Wonder (max) scores higher on seven of the nine metrics and GPT-5.6 Luna (ultra) on one, with one tie. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Muse Wonder (max) ahead, with a 4.8-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Muse Wonder (max) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 1.91 | 2.07 |
| Lowest script score | 78.2 Script 10 | 76.0 Script 7 |
| Highest script score | 82.2 Script 5 | 80.8 Script 9 |
| Range across scripts | 4.0 | 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 Muse Wonder (max) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | Muse Wonder (max) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.3 | 78.5 | +2.8 |
| Script 2 news-analysis / skeptical explainer | 81.7 | 80.3 | +1.4 |
| Script 3 personal roadmap / opinion | 81.3 | 79.7 | +1.6 |
| Script 4 short explainer | 79.5 | 77.4 | +2.1 |
| Script 5 news-analysis / opinion explainer | 82.2 | 79.7 | +2.5 |
| Script 6 founder announcement / personal origin story | 81.3 | 80.6 | +0.7 |
| Script 7 personal technical walkthrough / agentic workflow case study | 78.5 | 76.0 | +2.5 |
| Script 8 product release announcement / personal observation | 82.1 | 78.4 | +3.7 |
| Script 9 career guide / hiring analysis | 79.9 | 80.8 | -0.9 |
| Script 10 engineering process walkthrough / presentation adaptation | 78.2 | 76.9 | +1.3 |
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