Model Comparison
GPT-6.1 Terra vs DeepSeek V4 Pro 0813
Overlapping ranges: the best configurations, GPT-6.1 Terra (max) and DeepSeek V4 Pro 0813 (max), are 10 Elo apart, and their 95% ranges overlap. Among 84 models, each ranked by its best configuration, GPT-6.1 Terra is #23 and DeepSeek V4 Pro 0813 is #25. Cost per script: $0.079 for GPT-6.1 Terra (max) and $0.077 for DeepSeek V4 Pro 0813 (max).
Last updated , from board data generated at 20:15 UTC.
Picks and Verdict
Ranks in the picks and verdict are configuration ranks: each setting's place among all 141 configurations. The cards above give each model's rank.
PickGPT-6.1 Terra
GPT-6.1 Terra (low)
Pick GPT-6.1 Terra (low) as the default, since its individual Elo range overlaps DeepSeek's best and it costs $0.027 a script in 0.5 minutes.
PickDeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 (max)
Pick DeepSeek V4 Pro 0813 (max) when the script's flow matters more than the wait, since it scores above every Terra setting on YouTube structure and continuity, at $0.077.
The Elo point estimates are close, and GPT-6.1 Terra at low wins on price and speed. GPT-6.1 Terra (max) sits 10 Elo above DeepSeek V4 Pro 0813 (max) with overlapping 95% ranges, though that alone does not test the difference between the #23 model of 84 and the #25 model. Terra's five settings sit within 25 Elo of each other with overlapping ranges, and GPT-6.1 Terra (low) also sits 7 Elo above DeepSeek's best, inside overlapping ranges, for $0.027 a script against $0.077. It answers in 0.5 minutes, where DeepSeek thinks through 31,573 reasoning tokens and takes 8.9. DeepSeek's level matters a lot: DeepSeek V4 Pro 0813 (high) falls 597 Elo below its max, to #95 on the board. The metrics split. Terra at low writes with less filler, 6.6 points up on slop, and carries 3.4 more points of substance. DeepSeek leads YouTube structure by 2.6 points, hits the length 5.4 points better than Terra at low, and wins six of the ten scripts. I'd run Terra at low and get the draft about eight minutes sooner for about a third of the price.
Disclosure: GPT-6.1 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-6.1 Terra 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.
- Each bar describes one configuration. Overlap alone does not establish a tie or decide their order. Comparing these ranges does not directly test the difference between a pair.
- 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-6.1 Terra (max) | 1923 | 1884 to 1959 | 80.3 | $0.079 | 1.8 min | N/A | #43 |
| GPT-6.1 Terra (high) | 1922 | 1881 to 1958 | 80.3 | $0.027 | 0.5 min | N/A | #44 |
| GPT-6.1 Terra (low) | 1920 | 1879 to 1961 | 80.2 | $0.027 | 0.5 min | N/A | #46 |
| DeepSeek V4 Pro 0813 (max) | 1913 | 1869 to 1949 | 80.1 | $0.077 | 8.9 min | 31,573 | #47 |
| GPT-6.1 Terra (xhigh) | 1906 | 1869 to 1944 | 80.1 | $0.028 | 0.5 min | N/A | #48 |
| GPT-6.1 Terra (medium) | 1898 | 1852 to 1942 | 79.9 | $0.027 | 0.5 min | N/A | #49 |
| DeepSeek V4 Pro 0813 (high) | 1316 | 1235 to 1380 | 72.3 | $0.031 | 1.3 min | 8,879 | #95 |
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. The 95% ranges describe individual configurations; overlap alone establishes neither a tie nor an order for a pair.
- Best Configurations Head to Head. GPT-6.1 Terra (max) at Elo 1923 (range 1884 to 1959) and DeepSeek V4 Pro 0813 (max) at Elo 1913 (range 1869 to 1949) have overlapping 95% ranges.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, GPT-6.1 Terra (low) at Elo 1920 and $0.027 per script leads DeepSeek V4 Pro 0813 (high) at Elo 1316 and $0.031 per script by 604 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. GPT-6.1 Terra has the higher Writing Elo at every level name both models use: high and max. The 95% ranges do not overlap at high. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest Configuration Overlapping the Top One. GPT-6.1 Terra (high), at $0.027 per script, is the cheapest configuration whose 95% range overlaps that of GPT-6.1 Terra (max), at $0.079 per script: 1881 to 1958 against 1884 to 1959. GPT-6.1 Terra (max) costs about 2.9 times as much per script.
- Cheapest GPT-6.1 Terra Configuration Above DeepSeek V4 Pro 0813's Best. The cheapest GPT-6.1 Terra configuration with a higher Writing Elo than DeepSeek V4 Pro 0813 (max), at Elo 1913 and $0.077 per script, is GPT-6.1 Terra (high), at Elo 1922 and $0.027 per script. Their 95% ranges overlap. It costs less than the configuration it beats.
- Lowest to Highest Thinking Level. GPT-6.1 Terra moves +3 Elo from low to max, at about 2.9 times the cost per script. DeepSeek V4 Pro 0813 moves +597 Elo from high to max, at about 2.5 times the cost per script.
Writing Elo at Each Shared Level Name
| Level | GPT-6.1 Terra | DeepSeek V4 Pro 0813 | Gap | 95% Ranges |
|---|---|---|---|---|
| high | 1922 | 1316 | +606 | Separate |
| max | 1923 | 1913 | +10 | Overlap |
Gap is GPT-6.1 Terra minus DeepSeek V4 Pro 0813 at the same level name, using each model's highest-rated configuration at that level.
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-6.1 Terra (max) scores higher on five of the nine metrics and DeepSeek V4 Pro 0813 (max) on four. Weighted by each metric's share of the Writing Score, Substance, Accuracy & Value does the most to put GPT-6.1 Terra (max) ahead, with a 4.1-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| GPT-6.1 Terra (max) | DeepSeek V4 Pro 0813 (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.68 | 1.48 |
| Lowest script score | 77.9 Script 10 | 78.2 Script 10 |
| Highest script score | 83.2 Script 9 | 81.5 Script 6 |
| Range across scripts | 5.3 | 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 GPT-6.1 Terra (max) minus DeepSeek V4 Pro 0813 (max), and the higher score is in bold.
| Script | GPT-6.1 Terra (max) | DeepSeek V4 Pro 0813 (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 80.2 | 79.5 | +0.7 |
| Script 2 news-analysis / skeptical explainer | 80.7 | 80.6 | +0.1 |
| Script 3 personal roadmap / opinion | 80.4 | 80.8 | -0.4 |
| Script 4 short explainer | 79.6 | 78.5 | +1.1 |
| Script 5 news-analysis / opinion explainer | 80.1 | 80.9 | -0.8 |
| Script 6 founder announcement / personal origin story | 82.2 | 81.5 | +0.7 |
| Script 7 personal technical walkthrough / agentic workflow case study | 79.9 | 81.1 | -1.2 |
| Script 8 product release announcement / personal observation | 79.1 | 80.2 | -1.1 |
| Script 9 career guide / hiring analysis | 83.2 | 79.9 | +3.3 |
| Script 10 engineering process walkthrough / presentation adaptation | 77.9 | 78.2 | -0.3 |
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