Model Comparison
GPT-5.6 Terra vs DeepSeek V4.1 Flash
Too close to call: the best configurations, GPT-5.6 Terra (ultra) and DeepSeek V4.1 Flash (max), are 34 Elo apart, and their 95% ranges overlap. Among 78 models, each ranked by its best configuration, GPT-5.6 Terra is #13 and DeepSeek V4.1 Flash is #14. Cost per script: $0.275 for GPT-5.6 Terra (ultra) and $0.017 for DeepSeek V4.1 Flash (max).
Last updated , from board data generated at 01:13 UTC.
Picks and Verdict
PickGPT-5.6 Terra
GPT-5.6 Terra (medium)
Pick GPT-5.6 Terra (medium) when the facts matter most, since its 84.6 on Substance, Accuracy & Value beats every DeepSeek setting for $0.062 a script.
PickDeepSeek V4.1 Flash
DeepSeek V4.1 Flash (max)
Pick DeepSeek V4.1 Flash (max) as the everyday writer, since Terra's best costs about 16 times as much and the board can't separate the two.
I'd take DeepSeek V4.1 Flash here without much hesitation. GPT-5.6 Terra is the #13 model of 78 and DeepSeek V4.1 Flash the #14 model, each ranked by its best setting. GPT-5.6 Terra (ultra) rates 34 Elo above DeepSeek V4.1 Flash (max), and their 95% ranges overlap, so the board can't separate the two on writing. The prices are far apart: $0.017 a script against $0.275, about 16 times as much, and Terra takes about three times as long. Drop DeepSeek to high and its range still overlaps Terra at medium, for about a cent. More thinking pays off for DeepSeek, which climbs 402 Elo from no thinking to max and stays under two cents. Terra moves 76 Elo from medium to ultra at more than four times the cost, and those two ranges overlap as well. Terra's real edge is substance, almost four points up at the top, and visual cues. I'd run DeepSeek at max and keep its thinking on, because without it DeepSeek falls 360 Elo behind Terra at medium.
Disclosure: GPT-5.6 Terra 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 GPT-5.6 Terra and DeepSeek V4.1 Flash, 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 |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Terra (ultra) | 2074 | 2035 to 2113 | 81.4 | $0.275 | 8.0 min | N/A | #25 |
| DeepSeek V4.1 Flash (max) | 2040 | 1999 to 2076 | 81.0 | $0.017 | 2.4 min | 22,010 | #28 |
| GPT-5.6 Terra (medium) | 1998 | 1952 to 2041 | 80.7 | $0.062 | 1.4 min | N/A | #33 |
| 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 |
| DeepSeek V4.1 Flash (no thinking) | 1638 | 1588 to 1680 | 76.8 | $0.0037 | 0.3 min | 0 | #61 |
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. GPT-5.6 Terra (ultra) at Elo 2074 (range 2035 to 2113) and DeepSeek V4.1 Flash (max) at Elo 2040 (range 1999 to 2076) have overlapping 95% ranges, so the board cannot separate the two best configurations.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, GPT-5.6 Terra (medium) at Elo 1998 and $0.062 per script leads DeepSeek V4.1 Flash (no thinking) at Elo 1638 and $0.0037 per script by 360 Elo. Their 95% ranges do not overlap.
- Cheapest Configuration Overlapping the Top One. DeepSeek V4.1 Flash (max), at $0.017 per script, is the cheapest configuration whose 95% range overlaps that of GPT-5.6 Terra (ultra), at $0.275 per script: 1999 to 2076 against 2035 to 2113, so the board cannot separate them. GPT-5.6 Terra (ultra) costs about 16 times as much per script.
- Cheapest GPT-5.6 Terra Configuration Above DeepSeek V4.1 Flash's Best. The cheapest GPT-5.6 Terra configuration with a higher Writing Elo than DeepSeek V4.1 Flash (max), at Elo 2040 and $0.017 per script, is GPT-5.6 Terra (ultra), at Elo 2074 and $0.275 per script. Their 95% ranges overlap, so the board cannot separate them. It costs about 16 times as much per script.
- Lowest to Highest Thinking Level. GPT-5.6 Terra moves +76 Elo from medium to ultra, at about 4.4 times the cost per script. DeepSeek V4.1 Flash moves +402 Elo from no thinking to max, at about 4.6 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
GPT-5.6 Terra (ultra) scores higher on five of the nine metrics and DeepSeek V4.1 Flash (max) on four. Weighted by each metric's share of the Writing Score, Substance, Accuracy & Value does the most to put GPT-5.6 Terra (ultra) ahead, with a 3.9-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| GPT-5.6 Terra (ultra) | DeepSeek V4.1 Flash (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.38 | 1.30 |
| Lowest script score | 79.8 Script 4 | 79.7 Script 10 |
| Highest script score | 83.0 Script 6 | 82.4 Script 7 |
| Range across scripts | 3.2 | 2.7 |
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 GPT-5.6 Terra (ultra) minus DeepSeek V4.1 Flash (max), and the higher score is in bold.
| Script | GPT-5.6 Terra (ultra) | DeepSeek V4.1 Flash (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.1 | 80.8 | +0.3 |
| Script 2 news-analysis / skeptical explainer | 82.1 | 81.2 | +0.9 |
| Script 3 personal roadmap / opinion | 82.5 | 81.2 | +1.3 |
| Script 4 short explainer | 79.8 | 80.1 | -0.3 |
| Script 5 news-analysis / opinion explainer | 82.2 | 81.1 | +1.1 |
| Script 6 founder announcement / personal origin story | 83.0 | 80.8 | +2.2 |
| Script 7 personal technical walkthrough / agentic workflow case study | 80.6 | 82.4 | -1.8 |
| Script 8 product release announcement / personal observation | 80.3 | 80.7 | -0.4 |
| Script 9 career guide / hiring analysis | 81.8 | 82.2 | -0.4 |
| Script 10 engineering process walkthrough / presentation adaptation | 80.6 | 79.7 | +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