Model Comparison
Claude Opus 4.8 vs GPT-5.6 Luna
Claude Opus 4.8 (max effort) leads GPT-5.6 Luna (ultra) by 201 Elo, and their 95% ranges sit 119 Elo apart. Among 78 models, each ranked by its best configuration, Claude Opus 4.8 is #15 and GPT-5.6 Luna is #24. Cost per script: $1.23 for Claude Opus 4.8 (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 Opus 4.8
Claude Opus 4.8 (max effort)
Pick Claude Opus 4.8 (max effort) when the voice has to be close, because the 201 Elo lead only exists at this $1.23 setting.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) for everything else, because $0.026 a script gets a result the board can't separate from Opus at high.
Claude Opus 4.8 only has a clear lead over GPT-5.6 Luna's best at max effort, and max effort costs $1.23 a script. Up there it leads GPT-5.6 Luna (ultra) by 201 Elo with separate 95% ranges, the #15 model of 78 against the #24 model, each ranked by its best setting. Step down to Claude Opus 4.8 (high) and the lead shrinks to 56 Elo with overlapping ranges. The board can't separate Opus at high from Luna at ultra, and Opus at high costs $0.193 where Luna costs $0.026, about seven times as much. So the middle of this page goes to Luna on price. The two write differently, to be fair. Opus sounds more like me and structures the video better, four to five points on tone and YouTube Best Practices. Luna brings more substance, almost three points. One warning: GPT-5.6 Luna (medium) misses the target length badly and sits 203 Elo below ultra, so I wouldn't go under ultra to save two cents. For a script I'd record, Opus at max effort. For anything else here, Luna at ultra.
Disclosure: Claude Opus 4.8 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 Opus 4.8 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 Opus 4.8 (max effort) | 2013 | 1977 to 2047 | 80.7 | $1.23 | 9.8 min | #30 |
| Claude Opus 4.8 (high) | 1868 | 1827 to 1905 | 79.3 | $0.193 | 1.4 min | #44 |
| GPT-5.6 Luna (ultra) | 1812 | 1768 to 1858 | 78.8 | $0.026 | 3.1 min | #49 |
| 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 Opus 4.8 (max effort) leads GPT-5.6 Luna (ultra) by 201 Elo, and their 95% ranges do not overlap (1977 to 2047 against 1768 to 1858), which is strong evidence for that order.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Claude Opus 4.8 (high) at Elo 1868 and $0.193 per script leads GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script by 259 Elo. Their 95% ranges do not overlap.
- Cheapest Claude Opus 4.8 Configuration Above GPT-5.6 Luna's Best. The cheapest Claude Opus 4.8 configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1812 and $0.026 per script, is Claude Opus 4.8 (high), at Elo 1868 and $0.193 per script. Their 95% ranges overlap, so the board cannot separate them. It costs about 7.4 times as much per script.
- Lowest to Highest Thinking Level. Claude Opus 4.8 moves +145 Elo from high to max effort, at about 6.4 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 Opus 4.8 (max effort) scores higher on six of the nine metrics and GPT-5.6 Luna (ultra) on three. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Claude Opus 4.8 (max effort) 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
| Claude Opus 4.8 (max effort) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 2.02 | 2.07 |
| Lowest script score | 77.5 Script 4 | 76.0 Script 7 |
| Highest script score | 83.1 Script 6 | 80.8 Script 9 |
| Range across scripts | 5.6 | 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 Opus 4.8 (max effort) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | Claude Opus 4.8 (max effort) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 80.2 | 78.5 | +1.7 |
| Script 2 news-analysis / skeptical explainer | 80.6 | 80.3 | +0.3 |
| Script 3 personal roadmap / opinion | 79.3 | 79.7 | -0.4 |
| Script 4 short explainer | 77.5 | 77.4 | +0.1 |
| Script 5 news-analysis / opinion explainer | 80.3 | 79.7 | +0.6 |
| Script 6 founder announcement / personal origin story | 83.1 | 80.6 | +2.5 |
| Script 7 personal technical walkthrough / agentic workflow case study | 82.5 | 76.0 | +6.5 |
| Script 8 product release announcement / personal observation | 82.5 | 78.4 | +4.1 |
| Script 9 career guide / hiring analysis | 82.0 | 80.8 | +1.2 |
| Script 10 engineering process walkthrough / presentation adaptation | 78.9 | 76.9 | +2.0 |
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