Model Comparison
Grok 4.7 vs GPT-5.6 Luna
Grok 4.7 (medium) leads GPT-5.6 Luna (ultra) by 112 Elo, and their 95% ranges sit 5 Elo apart. Among 78 models, each ranked by its best configuration, Grok 4.7 is #22 and GPT-5.6 Luna is #24. Cost per script: $0.215 for Grok 4.7 (medium) and $0.026 for GPT-5.6 Luna (ultra).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickGrok 4.7
Grok 4.7 (medium)
Pick Grok 4.7 (medium) when sounding like me matters more than tidy prose, with tone at 78.4 against 71.9 for $0.215 a script.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) for a cheap, clean draft at $0.026 a script, and skip medium, which falls 203 Elo behind.
The answer here changes with the thinking level. At the top, Grok 4.7 (medium) leads GPT-5.6 Luna (ultra) by 112 Elo, and their 95% ranges sit 5 Elo apart, which is strong evidence for that order. Ranked by best setting, that is the #22 model of 78 against the #24 model. The bill runs the other way: $0.215 a script for Grok against $0.026 for Luna. Luna at ultra undercuts every Grok setting, and the board can't separate it from Grok 4.7 (high) or Grok 4.7 (low). Drop Luna to medium and that's gone. All three Grok settings beat it with ranges apart, and at medium, the one level name they share, the gap is 315 Elo. So Luna only competes at ultra. Even there, it gives up more than six points on matching my voice, while Grok gives up about three on writing craft and lands much further from the target length. For a cheap draft I'll rewrite anyway, I'd run Luna at ultra. If the voice has to be closer out of the box, Grok at medium is the one, at about eight times the price.
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 Grok 4.7 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 |
|---|---|---|---|---|---|---|---|
| Grok 4.7 (medium) | 1924 | 1863 to 1974 | 79.6 | $0.215 | 6.2 min | 27,687 | #42 |
| Grok 4.7 (high) | 1897 | 1850 to 1939 | 79.6 | $0.305 | 9.6 min | 42,549 | #43 |
| Grok 4.7 (low) | 1834 | 1784 to 1890 | 79.0 | $0.064 | 1.7 min | 2,760 | #48 |
| GPT-5.6 Luna (ultra) | 1812 | 1768 to 1858 | 78.8 | $0.026 | 3.1 min | N/A | #49 |
| GPT-5.6 Luna (medium) | 1609 | 1572 to 1647 | 76.7 | $0.0065 | 0.5 min | N/A | #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. 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. Grok 4.7 (medium) leads GPT-5.6 Luna (ultra) by 112 Elo, and their 95% ranges do not overlap (1863 to 1974 against 1768 to 1858), which is strong evidence for that order.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, Grok 4.7 (low) at Elo 1834 and $0.064 per script leads GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script by 225 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. At medium, the one level name both models use, Grok 4.7 has the higher Writing Elo: 1924 against 1609. Their 95% ranges do not overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest Configuration Overlapping the Top One. Grok 4.7 (low), at $0.064 per script, is the cheapest configuration whose 95% range overlaps that of Grok 4.7 (medium), at $0.215 per script: 1784 to 1890 against 1863 to 1974, so the board cannot separate them. Grok 4.7 (medium) costs about 3.4 times as much per script.
- Cheapest Grok 4.7 Configuration Above GPT-5.6 Luna's Best. The cheapest Grok 4.7 configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1812 and $0.026 per script, is Grok 4.7 (low), at Elo 1834 and $0.064 per script. Their 95% ranges overlap, so the board cannot separate them. It costs about 2.5 times as much per script.
- Lowest to Highest Thinking Level. Grok 4.7 moves +63 Elo from low to high, at about 4.8 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
Grok 4.7 (medium) 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 Grok 4.7 (medium) ahead, with a 6.5-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Grok 4.7 (medium) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 3.00 | 2.07 |
| Lowest script score | 75.6 Script 10 | 76.0 Script 7 |
| Highest script score | 82.2 Script 2 | 80.8 Script 9 |
| Range across scripts | 6.6 | 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 Grok 4.7 (medium) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | Grok 4.7 (medium) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.5 | 78.5 | +3.0 |
| Script 2 news-analysis / skeptical explainer | 82.2 | 80.3 | +1.9 |
| Script 3 personal roadmap / opinion | 81.6 | 79.7 | +1.9 |
| Script 4 short explainer | 76.9 | 77.4 | -0.5 |
| Script 5 news-analysis / opinion explainer | 80.5 | 79.7 | +0.8 |
| Script 6 founder announcement / personal origin story | 82.0 | 80.6 | +1.4 |
| Script 7 personal technical walkthrough / agentic workflow case study | 76.5 | 76.0 | +0.5 |
| Script 8 product release announcement / personal observation | 79.0 | 78.4 | +0.6 |
| Script 9 career guide / hiring analysis | 80.2 | 80.8 | -0.6 |
| Script 10 engineering process walkthrough / presentation adaptation | 75.6 | 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