Model Comparison
DeepSeek V4.1 Flash vs GPT-5.6 Luna
DeepSeek V4.1 Flash (max) leads GPT-5.6 Luna (ultra) by 228 Elo, and their 95% ranges sit 141 Elo apart. Among 78 models, each ranked by its best configuration, DeepSeek V4.1 Flash is #14 and GPT-5.6 Luna is #24. Cost per script: $0.017 for DeepSeek V4.1 Flash (max) and $0.026 for GPT-5.6 Luna (ultra).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickDeepSeek V4.1 Flash
DeepSeek V4.1 Flash (high)
Pick DeepSeek V4.1 Flash (high) for everyday drafts, at $0.012 a script and about a minute each.
PickGPT-5.6 Luna
GPT-5.6 Luna (ultra)
Pick GPT-5.6 Luna (ultra) when the facts matter more than the voice, since its substance score of 84.8 is the highest on the page.
DeepSeek V4.1 Flash wins this one on the writing, and the price doesn't rescue GPT-5.6 Luna. DeepSeek V4.1 Flash (max) leads GPT-5.6 Luna (ultra) by 228 Elo, with 95% ranges that don't overlap, and it's the cheaper and quicker of the two, $0.017 a script against $0.026. Each ranked by its best setting, DeepSeek V4.1 Flash is the #14 model of 78 and GPT-5.6 Luna the #24 model. Lower down it gets worse for Luna. DeepSeek V4.1 Flash (low) rates 44 Elo above Luna's best setting. Those two ranges overlap, so the board cannot separate them, but low costs less than a third as much and finishes in under a minute where ultra takes more than three. Luna's real strength is substance. At the top settings it leads there by more than two points, and its hook is a touch stronger too. DeepSeek leads by more than six points on tone, which weighs the most in the Writing Score and is harder to repair in an edit. I'd run DeepSeek at high, since its range overlaps the max setting's and it takes less than half the time.
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 DeepSeek V4.1 Flash 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 |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash (max) | 2040 | 1999 to 2076 | 81.0 | $0.017 | 2.4 min | 22,010 | #28 |
| DeepSeek V4.1 Flash (high) | 1971 | 1925 to 2010 | 80.3 | $0.012 | 1.1 min | 13,809 | #38 |
| DeepSeek V4.1 Flash (low) | 1856 | 1815 to 1906 | 79.3 | $0.0077 | 0.7 min | 6,740 | #46 |
| GPT-5.6 Luna (ultra) | 1812 | 1768 to 1858 | 78.8 | $0.026 | 3.1 min | N/A | #49 |
| DeepSeek V4.1 Flash (no thinking) | 1638 | 1588 to 1680 | 76.8 | $0.0037 | 0.3 min | 0 | #61 |
| 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. DeepSeek V4.1 Flash (max) leads GPT-5.6 Luna (ultra) by 228 Elo, and their 95% ranges do not overlap (1999 to 2076 against 1768 to 1858), which is strong evidence for that order.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, DeepSeek V4.1 Flash (no thinking) at Elo 1638 and $0.0037 per script leads GPT-5.6 Luna (medium) at Elo 1609 and $0.0065 per script by 29 Elo. Their 95% ranges overlap, so the board cannot separate them.
- Cheapest Configuration Overlapping the Top One. DeepSeek V4.1 Flash (high), at $0.012 per script, is the cheapest configuration whose 95% range overlaps that of DeepSeek V4.1 Flash (max), at $0.017 per script: 1925 to 2010 against 1999 to 2076, so the board cannot separate them. DeepSeek V4.1 Flash (max) costs about 1.4 times as much per script.
- Cheapest DeepSeek V4.1 Flash Configuration Above GPT-5.6 Luna's Best. The cheapest DeepSeek V4.1 Flash configuration with a higher Writing Elo than GPT-5.6 Luna (ultra), at Elo 1812 and $0.026 per script, is DeepSeek V4.1 Flash (low), at Elo 1856 and $0.0077 per script. Their 95% ranges overlap, so the board cannot separate them. It costs less than the configuration it beats.
- Lowest to Highest Thinking Level. DeepSeek V4.1 Flash moves +402 Elo from no thinking to max, at about 4.6 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
DeepSeek V4.1 Flash (max) scores higher on five of the nine metrics and GPT-5.6 Luna (ultra) on four. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put DeepSeek V4.1 Flash (max) ahead, with a 6.2-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| DeepSeek V4.1 Flash (max) | GPT-5.6 Luna (ultra) | |
|---|---|---|
| Score spread across drafts (±) | 1.30 | 2.07 |
| Lowest script score | 79.7 Script 10 | 76.0 Script 7 |
| Highest script score | 82.4 Script 7 | 80.8 Script 9 |
| Range across scripts | 2.7 | 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 DeepSeek V4.1 Flash (max) minus GPT-5.6 Luna (ultra), and the higher score is in bold.
| Script | DeepSeek V4.1 Flash (max) | GPT-5.6 Luna (ultra) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 80.8 | 78.5 | +2.3 |
| Script 2 news-analysis / skeptical explainer | 81.2 | 80.3 | +0.9 |
| Script 3 personal roadmap / opinion | 81.2 | 79.7 | +1.5 |
| Script 4 short explainer | 80.1 | 77.4 | +2.7 |
| Script 5 news-analysis / opinion explainer | 81.1 | 79.7 | +1.4 |
| Script 6 founder announcement / personal origin story | 80.8 | 80.6 | +0.2 |
| Script 7 personal technical walkthrough / agentic workflow case study | 82.4 | 76.0 | +6.4 |
| Script 8 product release announcement / personal observation | 80.7 | 78.4 | +2.3 |
| Script 9 career guide / hiring analysis | 82.2 | 80.8 | +1.4 |
| Script 10 engineering process walkthrough / presentation adaptation | 79.7 | 76.9 | +2.8 |
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