Model Comparison
DeepSeek V4.1 Flash 1017 vs GPT-6.1 Terra
DeepSeek V4.1 Flash 1017 (max) leads GPT-6.1 Terra (max) by 149 Elo, and their 95% ranges sit 71 Elo apart. Even DeepSeek V4.1 Flash 1017's lowest-rated configuration, DeepSeek V4.1 Flash 1017 (high), ranks above GPT-6.1 Terra (max). Among 84 models, each ranked by its best configuration, DeepSeek V4.1 Flash 1017 is #14 and GPT-6.1 Terra is #23. Cost per script: $0.014 for DeepSeek V4.1 Flash 1017 (max) and $0.079 for GPT-6.1 Terra (max).
Last updated , from board data generated at 20:15 UTC.
Picks and Verdict
PickDeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 (max)
Pick DeepSeek V4.1 Flash 1017 (max) as the everyday writer, 149 Elo above Terra's best with separate ranges, at $0.014 a script.
PickGPT-6.1 Terra
GPT-6.1 Terra (low)
Pick GPT-6.1 Terra (low) when speed or facts come first, at about half a minute a script and 85.1 on Substance, Accuracy & Value, above both DeepSeek settings.
DeepSeek V4.1 Flash 1017 writes the better script and costs less, so this one is easy. DeepSeek V4.1 Flash 1017 is the #14 model of 84 and GPT-6.1 Terra the #23 model, each ranked by its best setting. DeepSeek V4.1 Flash 1017 (max) sits 149 Elo above GPT-6.1 Terra (max), with 95% ranges 71 Elo apart, and even DeepSeek at high clears every Terra row. Neither model gets much from more effort. DeepSeek's high and max overlap, 41 Elo apart, and Terra's five levels sit within 25 Elo of each other with overlapping ranges, so on Terra I would run low. Price goes DeepSeek's way too: $0.014 a script at max, against $0.027 for Terra at low and $0.079 at max. Terra's real advantage is speed, about half a minute a script against 1.3 minutes for DeepSeek at max. DeepSeek leads on Tone & Voice Match by 5.2 points at the top settings. Terra carries more substance, 3.5 points up, less slop and better visual cues. I'd run DeepSeek at max for everyday scripts and reach for Terra at low only when I need the draft back fast or the facts carry the video.
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 DeepSeek V4.1 Flash 1017 and GPT-6.1 Terra, 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 |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 (max) | 2072 | 2030 to 2120 | 81.6 | $0.014 | 1.3 min | 16,960 | #25 |
| DeepSeek V4.1 Flash 1017 (high) | 2031 | 1978 to 2075 | 81.1 | $0.0095 | 0.9 min | 9,728 | #28 |
| 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 |
| 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 |
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. DeepSeek V4.1 Flash 1017 (max) leads GPT-6.1 Terra (max) by 149 Elo, and their 95% ranges do not overlap (2030 to 2120 against 1884 to 1959), which is strong evidence for that order.
- Every DeepSeek V4.1 Flash 1017 Configuration Ranks Higher. Both DeepSeek V4.1 Flash 1017 configurations rank above all five GPT-6.1 Terra configurations: the lowest-rated, DeepSeek V4.1 Flash 1017 (high) at Elo 2031, still beats GPT-6.1 Terra (max) at Elo 1923. Their 95% ranges do not overlap.
- Lowest Thinking Levels Head to Head. At their lowest thinking levels, DeepSeek V4.1 Flash 1017 (high) at Elo 2031 and $0.0095 per script leads GPT-6.1 Terra (low) at Elo 1920 and $0.027 per script by 111 Elo. Their 95% ranges do not overlap.
- Same Level Name, Side by Side. DeepSeek V4.1 Flash 1017 has the higher Writing Elo at every level name both models use: high and max. The 95% ranges do not overlap at any of them. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Cheapest Configuration Overlapping the Top One. DeepSeek V4.1 Flash 1017 (high), at $0.0095 per script, is the cheapest configuration whose 95% range overlaps that of DeepSeek V4.1 Flash 1017 (max), at $0.014 per script: 1978 to 2075 against 2030 to 2120. DeepSeek V4.1 Flash 1017 (max) costs about 1.5 times as much per script.
- Cheapest DeepSeek V4.1 Flash 1017 Configuration Above GPT-6.1 Terra's Best. The cheapest DeepSeek V4.1 Flash 1017 configuration with a higher Writing Elo than GPT-6.1 Terra (max), at Elo 1923 and $0.079 per script, is DeepSeek V4.1 Flash 1017 (high), at Elo 2031 and $0.0095 per script. It costs less than the configuration it beats.
- Lowest to Highest Thinking Level. DeepSeek V4.1 Flash 1017 moves +41 Elo from high to max, at about 1.5 times the cost per script. GPT-6.1 Terra moves +3 Elo from low to max, at about 2.9 times the cost per script.
Writing Elo at Each Shared Level Name
| Level | DeepSeek V4.1 Flash 1017 | GPT-6.1 Terra | Gap | 95% Ranges |
|---|---|---|---|---|
| high | 2031 | 1922 | +109 | Separate |
| max | 2072 | 1923 | +149 | Separate |
Gap is DeepSeek V4.1 Flash 1017 minus GPT-6.1 Terra 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
DeepSeek V4.1 Flash 1017 (max) scores higher on six of the nine metrics and GPT-6.1 Terra (max) on three. Weighted by each metric's share of the Writing Score, Tone & Voice Match does the most to put DeepSeek V4.1 Flash 1017 (max) ahead, with a 5.2-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| DeepSeek V4.1 Flash 1017 (max) | GPT-6.1 Terra (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.58 | 1.68 |
| Lowest script score | 79.9 Script 4 | 77.9 Script 10 |
| Highest script score | 83.0 Script 7 | 83.2 Script 9 |
| Range across scripts | 3.1 | 5.3 |
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 DeepSeek V4.1 Flash 1017 (max) minus GPT-6.1 Terra (max), and the higher score is in bold.
| Script | DeepSeek V4.1 Flash 1017 (max) | GPT-6.1 Terra (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 80.5 | 80.2 | +0.3 |
| Script 2 news-analysis / skeptical explainer | 80.8 | 80.7 | +0.1 |
| Script 3 personal roadmap / opinion | 80.5 | 80.4 | +0.1 |
| Script 4 short explainer | 79.9 | 79.6 | +0.3 |
| Script 5 news-analysis / opinion explainer | 82.9 | 80.1 | +2.8 |
| Script 6 founder announcement / personal origin story | 81.2 | 82.2 | -1.0 |
| Script 7 personal technical walkthrough / agentic workflow case study | 83.0 | 79.9 | +3.1 |
| Script 8 product release announcement / personal observation | 82.6 | 79.1 | +3.5 |
| Script 9 career guide / hiring analysis | 83.0 | 83.2 | -0.2 |
| Script 10 engineering process walkthrough / presentation adaptation | 81.6 | 77.9 | +3.7 |
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