Model Comparison
Claude Fable 5.1 vs GPT-5.6 Luna
Claude Fable 5.1 (max effort) leads GPT-5.6 Luna (ultra) by 741 Elo, and their 95% ranges sit 655 Elo apart. Even Claude Fable 5.1's lowest-rated configuration, Claude Fable 5.1 (high), ranks above GPT-5.6 Luna (ultra). Among 78 models, each ranked by its best configuration, Claude Fable 5.1 is #3 and GPT-5.6 Luna is #24. Cost per script: $3.56 for Claude Fable 5.1 (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 Fable 5.1
Claude Fable 5.1 (max effort)
Pick Claude Fable 5.1 (max effort) for the scripts you publish, where its 9.9-point lead on Tone & Voice Match over Luna's best matters most, at $3.56 a script.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) for cheap first drafts with substance close to Fable's, at $0.026 a script in about three minutes.
Voice decides this one. At their best settings, Claude Fable 5.1 leads GPT-5.6 Luna by 9.9 points on Tone & Voice Match, the widest metric gap between them. Claude Fable 5.1 is the #3 model of 78 and GPT-5.6 Luna the #24 model, 741 Elo apart at their best, and both Fable settings rate above both Luna settings with separate 95% ranges. Luna does hold its own in two places. At medium its Hook Strength edges Fable's best, and at ultra its substance sits within a point and a half of both Fable settings, which is a lot to get for $0.026 a script. In each model, the top setting is the one I'd run. Fable at max effort sits 201 Elo above high with a separate range and steadier drafts, for nearly twice the price. Luna gains 203 Elo from medium to ultra for under two cents more, and ultra fixes medium's length problem. At $3.56 a script, Fable at max effort costs more than a hundred times what Luna does, so my split is easy: Fable for anything I publish, Luna at ultra for cheap first drafts.
Disclosure: Claude Fable 5.1 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 Fable 5.1 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 Fable 5.1 (max effort) | 2553 | 2513 to 2587 | 84.5 | $3.56 | 12.3 min | #4 |
| Claude Fable 5.1 (high) | 2352 | 2302 to 2403 | 83.4 | $1.85 | 6.3 min | #9 |
| 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 Fable 5.1 (max effort) leads GPT-5.6 Luna (ultra) by 741 Elo, and their 95% ranges do not overlap (2513 to 2587 against 1768 to 1858), which is strong evidence for that order.
- Every Claude Fable 5.1 Configuration Ranks Higher. Both Claude Fable 5.1 configurations rank above both GPT-5.6 Luna configurations: the lowest-rated, Claude Fable 5.1 (high) at Elo 2352, still beats GPT-5.6 Luna (ultra) at Elo 1812. Their 95% ranges do not overlap.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Claude Fable 5.1 (high) at Elo 2352 and $1.85 per script leads GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script by 743 Elo. Their 95% ranges do not overlap.
- Cheapest Claude Fable 5.1 Configuration Above GPT-5.6 Luna's Best. The cheapest Claude Fable 5.1 configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1812 and $0.026 per script, is Claude Fable 5.1 (high), at Elo 2352 and $1.85 per script. It costs about 71 times as much per script.
- Lowest to Highest Thinking Level. Claude Fable 5.1 moves +201 Elo from high to max effort, at about 1.9 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 Fable 5.1 (max effort) scores higher on all nine metrics. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Claude Fable 5.1 (max effort) ahead, with a 9.9-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Claude Fable 5.1 (max effort) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 1.13 | 2.07 |
| Lowest script score | 82.8 Script 10 | 76.0 Script 7 |
| Highest script score | 86.2 Script 9 | 80.8 Script 9 |
| Range across scripts | 3.4 | 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 Fable 5.1 (max effort) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | Claude Fable 5.1 (max effort) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 83.3 | 78.5 | +4.8 |
| Script 2 news-analysis / skeptical explainer | 83.8 | 80.3 | +3.5 |
| Script 3 personal roadmap / opinion | 84.0 | 79.7 | +4.3 |
| Script 4 short explainer | 85.2 | 77.4 | +7.8 |
| Script 5 news-analysis / opinion explainer | 84.9 | 79.7 | +5.2 |
| Script 6 founder announcement / personal origin story | 85.0 | 80.6 | +4.4 |
| Script 7 personal technical walkthrough / agentic workflow case study | 85.3 | 76.0 | +9.3 |
| Script 8 product release announcement / personal observation | 84.7 | 78.4 | +6.3 |
| Script 9 career guide / hiring analysis | 86.2 | 80.8 | +5.4 |
| Script 10 engineering process walkthrough / presentation adaptation | 82.8 | 76.9 | +5.9 |
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