Model Comparison
Claude Haiku 5.5 vs GPT-5.6 Luna
Claude Haiku 5.5 (max effort) leads GPT-5.6 Luna (ultra) by 197 Elo, and their 95% ranges sit 114 Elo apart. Among 78 models, each ranked by its best configuration, Claude Haiku 5.5 is #16 and GPT-5.6 Luna is #24. Cost per script: $0.103 for Claude Haiku 5.5 (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 Haiku 5.5
Claude Haiku 5.5 (xhigh)
Pick Claude Haiku 5.5 (xhigh) for cheap scripts that still need the right tone, since it rates 115 Elo above Luna's best, with separate ranges, at $0.029 a script.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) for hook-first drafts at $0.026 a script, since its 80.6 on Hook Strength beats every Haiku setting.
Both of these are budget models, and the better buy costs a fraction of a cent more. Claude Haiku 5.5 (max effort) rates 197 Elo above GPT-5.6 Luna (ultra), the #16 model of 78 against the #24 model, and their 95% ranges sit well apart, strong evidence for that order. I wouldn't pay for max effort, though. It takes more than twelve minutes and costs about three and a half times what Claude Haiku 5.5 (xhigh) does. Haiku at xhigh costs $0.029 against Luna's $0.026, runs about as fast, and still rates 115 Elo above Luna's best with separate ranges. Step Haiku down to save money and Luna has the better of it: Luna at ultra is 89 Elo above Claude Haiku 5.5 (high) with separate ranges. At medium, the one level name they share, both cost under a cent and their ranges overlap, though Luna's Length Adherence drops to 70.9 there. Luna's edge is the hook, two to three points up on Haiku's top two settings. Haiku is closer to my tone by about four points. For anything past a rough draft, I'd run Haiku at xhigh.
Disclosure: Claude Haiku 5.5 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 Haiku 5.5 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 Haiku 5.5 (max effort) | 2009 | 1972 to 2044 | 80.8 | $0.103 | 12.6 min | #31 |
| Claude Haiku 5.5 (xhigh) | 1927 | 1883 to 1965 | 80.0 | $0.029 | 3.6 min | #41 |
| GPT-5.6 Luna (ultra) | 1812 | 1768 to 1858 | 78.8 | $0.026 | 3.1 min | #49 |
| Claude Haiku 5.5 (high) | 1723 | 1679 to 1760 | 78.0 | $0.012 | 1.5 min | #53 |
| Claude Haiku 5.5 (medium) | 1620 | 1572 to 1670 | 76.7 | $0.0067 | 0.8 min | #62 |
| GPT-5.6 Luna (medium) | 1609 | 1572 to 1647 | 76.7 | $0.0065 | 0.5 min | #66 |
| Claude Haiku 5.5 (low) | 1504 | 1461 to 1550 | 75.2 | $0.0045 | 0.5 min | #74 |
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 Haiku 5.5 (max effort) leads GPT-5.6 Luna (ultra) by 197 Elo, and their 95% ranges do not overlap (1972 to 2044 against 1768 to 1858), which is strong evidence for that order.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script leads Claude Haiku 5.5 (low) at Elo 1504 and $0.0045 per script by 105 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. At medium, the one level name both models use, Claude Haiku 5.5 has the higher Writing Elo: 1620 against 1609. Their 95% ranges overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest Claude Haiku 5.5 Configuration Above GPT-5.6 Luna's Best. The cheapest Claude Haiku 5.5 configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1812 and $0.026 per script, is Claude Haiku 5.5 (xhigh), at Elo 1927 and $0.029 per script. The two cost about the same per script.
- Lowest to Highest Thinking Level. Claude Haiku 5.5 moves +505 Elo from low to max effort, at about 23 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 Haiku 5.5 (max effort) scores higher on eight of the nine metrics and GPT-5.6 Luna (ultra) on one. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put Claude Haiku 5.5 (max effort) ahead, with a 4.5-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Claude Haiku 5.5 (max effort) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 1.55 | 2.07 |
| Lowest script score | 78.2 Script 10 | 76.0 Script 7 |
| Highest script score | 82.6 Script 4 | 80.8 Script 9 |
| Range across scripts | 4.4 | 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 Haiku 5.5 (max effort) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | Claude Haiku 5.5 (max effort) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 80.3 | 78.5 | +1.8 |
| Script 2 news-analysis / skeptical explainer | 80.7 | 80.3 | +0.4 |
| Script 3 personal roadmap / opinion | 80.8 | 79.7 | +1.1 |
| Script 4 short explainer | 82.6 | 77.4 | +5.2 |
| Script 5 news-analysis / opinion explainer | 81.7 | 79.7 | +2.0 |
| Script 6 founder announcement / personal origin story | 81.1 | 80.6 | +0.5 |
| Script 7 personal technical walkthrough / agentic workflow case study | 80.0 | 76.0 | +4.0 |
| Script 8 product release announcement / personal observation | 81.3 | 78.4 | +2.9 |
| Script 9 career guide / hiring analysis | 81.5 | 80.8 | +0.7 |
| 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