Model Comparison
Grok 4.6 vs DeepSeek V4 Pro 0813
Too close to call: the best configurations, Grok 4.6 (high) and DeepSeek V4 Pro 0813 (max), are 28 Elo apart, and their 95% ranges overlap. Among 78 models, each ranked by its best configuration, Grok 4.6 is #19 and DeepSeek V4 Pro 0813 is #21. Cost per script: $0.156 for Grok 4.6 (high) and $0.077 for DeepSeek V4 Pro 0813 (max).
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) when the voice has to be right in the first draft, since it leads DeepSeek by 2.5 points on Tone & Voice Match for $0.156 a script.
PickDeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 (max)
Pick DeepSeek V4 Pro 0813 (max) as the default, since the board can't separate it from Grok 4.6 (high) and it costs $0.077 a script with steadier drafts.
Grok 4.6 sounds more like me, and DeepSeek V4 Pro 0813 costs about half as much. The board can't separate the two, so that's what I'd choose on. With each of the 78 models ranked by its best setting, Grok 4.6 is the #19 model and DeepSeek V4 Pro 0813 the #21 model. Grok 4.6 (high), its only setting on the board, sits 28 Elo above DeepSeek V4 Pro 0813 (max) with overlapping 95% ranges. Grok leads Tone & Voice Match, the metric with the most weight, by 2.5 points, and substance by 3.3. It's also almost four minutes faster. DeepSeek answers with cleaner sentences, 2.5 points up on craft, and slightly steadier drafts: Grok's scores spread about a quarter more. Then there's the price, $0.077 a script against $0.156. The one level name they share doesn't tell you much. At high Grok leads by 628 Elo, but high is DeepSeek's lowest setting, and max adds 600 Elo to it. I'd default to DeepSeek at max and pay for Grok when the voice has to be right in the first draft.
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 DeepSeek V4 Pro 0813, 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 |
| DeepSeek V4 Pro 0813 (max) | 1950 | 1906 to 1989 | 80.1 | $0.077 | 8.9 min | 31,573 | #40 |
| DeepSeek V4 Pro 0813 (high) | 1350 | 1272 to 1428 | 72.3 | $0.031 | 1.3 min | 8,879 | #81 |
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 DeepSeek V4 Pro 0813 (max) at Elo 1950 (range 1906 to 1989) 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 1350. 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. DeepSeek V4 Pro 0813 (max), at $0.077 per script, is the cheapest configuration whose 95% range overlaps that of Grok 4.6 (high), at $0.156 per script: 1906 to 1989 against 1930 to 2023, so the board cannot separate them. Grok 4.6 (high) costs about 2 times as much per script.
- Lowest to Highest Thinking Level. DeepSeek V4 Pro 0813 moves +600 Elo from high to max, at about 2.5 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 three of the nine metrics and DeepSeek V4 Pro 0813 (max) on six. Weighted by each metric's share of the Writing Score, Substance, Accuracy & Value does the most to put Grok 4.6 (high) ahead, with a 3.3-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Grok 4.6 (high) | DeepSeek V4 Pro 0813 (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.82 | 1.48 |
| Lowest script score | 78.5 Script 3 | 78.2 Script 10 |
| Highest script score | 82.8 Script 6 | 81.5 Script 6 |
| Range across scripts | 4.3 | 3.3 |
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 DeepSeek V4 Pro 0813 (max), and the higher score is in bold.
| Script | Grok 4.6 (high) | DeepSeek V4 Pro 0813 (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.6 | 79.5 | +2.1 |
| Script 2 news-analysis / skeptical explainer | 80.8 | 80.6 | +0.2 |
| Script 3 personal roadmap / opinion | 78.5 | 80.8 | -2.3 |
| Script 4 short explainer | 80.2 | 78.5 | +1.7 |
| Script 5 news-analysis / opinion explainer | 81.1 | 80.9 | +0.2 |
| Script 6 founder announcement / personal origin story | 82.8 | 81.5 | +1.3 |
| Script 7 personal technical walkthrough / agentic workflow case study | 79.0 | 81.1 | -2.1 |
| Script 8 product release announcement / personal observation | 79.7 | 80.2 | -0.5 |
| Script 9 career guide / hiring analysis | 80.4 | 79.9 | +0.5 |
| Script 10 engineering process walkthrough / presentation adaptation | 79.1 | 78.2 | +0.9 |
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