Model Comparison
Grok 4.6 vs Grok 4.7
Too close to call: the best configurations, Grok 4.6 (high) and Grok 4.7 (medium), are 54 Elo apart, and their 95% ranges overlap. Among 78 models, each ranked by its best configuration, Grok 4.6 is #19 and Grok 4.7 is #22. Cost per script: $0.156 for Grok 4.6 (high) and $0.215 for Grok 4.7 (medium).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickGrok 4.6
Grok 4.6 (high)
Pick Grok 4.6 (high) if you want a Grok, since it ranks above all three Grok 4.7 settings at $0.156 a script.
PickGrok 4.7
Grok 4.7 (medium)
Pick Grok 4.7 (medium) for scripts that need the most substance, since its 86.2 there is the best on this page at $0.215 a script.
The newer Grok doesn't beat the older one here. Grok 4.6 is the #19 model of 78 and Grok 4.7 the #22 model, each ranked by its best setting. Grok 4.6 (high) sits 54 Elo above Grok 4.7 (medium), the newer model's best setting, and their 95% ranges overlap, so the board cannot separate them. The cost order is clearer. Grok 4.7 at medium costs $0.215 a script against $0.156 for Grok 4.6. Stepping up doesn't help the newer model. Grok 4.7 (high) costs about twice what Grok 4.6 does, takes almost twice as long, and burns more than twice the reasoning tokens for a Writing Elo 81 points lower. Grok 4.7 (low) is the odd one. It has the best hook score on this page, then misses the requested length by a wide margin and ends 144 Elo under Grok 4.6 with separate ranges. Grok 4.7 at medium does carry a bit more substance, about a point. Both models share a weak spot in writing craft, and Grok 4.7 at medium is the weaker of the two there. I'd keep Grok 4.6 at high and skip the upgrade.
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 4.6 and Grok 4.7, 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 4.6 (high) | 1978 | 1930 to 2023 | 80.3 | $0.156 | 5.2 min | 18,588 | #36 |
| 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 |
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. Grok 4.6 (high) at Elo 1978 (range 1930 to 2023) and Grok 4.7 (medium) at Elo 1924 (range 1863 to 1974) have overlapping 95% ranges, so the board cannot separate the two best configurations.
- Same Level Name, Side by Side. At high, the one level name both models use, Grok 4.6 has the higher Writing Elo: 1978 against 1897. Their 95% ranges overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Lowest to Highest Thinking Level. Grok 4.7 moves +63 Elo from low to high, at about 4.8 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 4.6 (high) scores higher on four of the nine metrics and Grok 4.7 (medium) on five. Weighted by each metric's share of the Writing Score, Length Adherence does the most to put Grok 4.6 (high) ahead, with a 12.0-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Grok 4.6 (high) | Grok 4.7 (medium) | |
|---|---|---|
| Score spread across drafts (±) | 1.82 | 3.00 |
| Lowest script score | 78.5 Script 3 | 75.6 Script 10 |
| Highest script score | 82.8 Script 6 | 82.2 Script 2 |
| Range across scripts | 4.3 | 6.6 |
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 4.6 (high) minus Grok 4.7 (medium), and the higher score is in bold.
| Script | Grok 4.6 (high) | Grok 4.7 (medium) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.6 | 81.5 | +0.1 |
| Script 2 news-analysis / skeptical explainer | 80.8 | 82.2 | -1.4 |
| Script 3 personal roadmap / opinion | 78.5 | 81.6 | -3.1 |
| Script 4 short explainer | 80.2 | 76.9 | +3.3 |
| Script 5 news-analysis / opinion explainer | 81.1 | 80.5 | +0.6 |
| Script 6 founder announcement / personal origin story | 82.8 | 82.0 | +0.8 |
| Script 7 personal technical walkthrough / agentic workflow case study | 79.0 | 76.5 | +2.5 |
| Script 8 product release announcement / personal observation | 79.7 | 79.0 | +0.7 |
| Script 9 career guide / hiring analysis | 80.4 | 80.2 | +0.2 |
| Script 10 engineering process walkthrough / presentation adaptation | 79.1 | 75.6 | +3.5 |
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