Model Comparison
Kimi K3.1 Pro vs DeepSeek V4.1 Flash
Kimi K3.1 Pro (max) leads DeepSeek V4.1 Flash (max) by 193 Elo, and their 95% ranges sit 114 Elo apart. Among 83 models, each ranked by its best configuration, Kimi K3.1 Pro is #7 and DeepSeek V4.1 Flash is #16. Cost per script: $0.251 for Kimi K3.1 Pro (max) and $0.017 for DeepSeek V4.1 Flash (max).
Last updated , from board data generated at 22:06 UTC.
Picks and Verdict
PickKimi K3.1 Pro
Kimi K3.1 Pro (max)
Pick Kimi K3.1 Pro (max) for the final draft, where a 193 Elo lead over DeepSeek's best is worth $0.251 a script.
PickDeepSeek V4.1 Flash
DeepSeek V4.1 Flash (max)
Pick DeepSeek V4.1 Flash (max) for daily drafting at $0.017 a script and 2.4 minutes, with slightly better tone and steadier drafts.
DeepSeek V4.1 Flash costs pennies, and it still can't keep up with Kimi K3.1 Pro on the page. Kimi K3.1 Pro (max) leads DeepSeek V4.1 Flash (max) by 193 Elo with separate 95% ranges and wins nine of the ten scripts, the #7 model of 83 against the #16 model, each ranked by its best configuration. DeepSeek's $0.017 and 2.4 minutes a script compare with $0.251 and 5.5 minutes for Kimi, about 15 times the price. DeepSeek even spends more reasoning tokens at max, 22,010 against 19,487, and still lands well below. Its thinking pays, with 386 Elo from no thinking to max, so I'd only run it at max. Kimi's single max row still tops all four DeepSeek settings. Most of the gap is content. Kimi is almost nine points ahead on visual cues and over five on substance, with stronger hooks. DeepSeek is about a point ahead on tone, and its drafts are steadier. I'd keep Kimi for the final draft and run DeepSeek at max for everything else.
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 Kimi K3.1 Pro 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 |
|---|---|---|---|---|---|---|---|
| Kimi K3.1 Pro (max) | 2205 | 2166 to 2246 | 82.5 | $0.251 | 5.5 min | 19,487 | #14 |
| DeepSeek V4.1 Flash (max) | 2012 | 1971 to 2052 | 81.0 | $0.017 | 2.4 min | 22,010 | #32 |
| DeepSeek V4.1 Flash (high) | 1938 | 1897 to 1975 | 80.3 | $0.012 | 1.1 min | 13,809 | #42 |
| DeepSeek V4.1 Flash (low) | 1839 | 1782 to 1895 | 79.3 | $0.0077 | 0.7 min | 6,740 | #49 |
| DeepSeek V4.1 Flash (no thinking) | 1626 | 1581 to 1669 | 76.8 | $0.0037 | 0.3 min | 0 | #65 |
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. Kimi K3.1 Pro (max) leads DeepSeek V4.1 Flash (max) by 193 Elo, and their 95% ranges do not overlap (2166 to 2246 against 1971 to 2052), which is strong evidence for that order.
- Every Kimi K3.1 Pro Configuration Ranks Higher. Kimi K3.1 Pro (max), the only Kimi K3.1 Pro configuration on the board, ranks above all four DeepSeek V4.1 Flash configurations, including DeepSeek V4.1 Flash (max) at Elo 2012.
- Same Level Name, Side by Side. At max, the one level name both models use, Kimi K3.1 Pro has the higher Writing Elo: 2205 against 2012. Their 95% ranges do not overlap there. Level names come from each provider, so the same name does not promise the same reasoning budget.
- Lowest to Highest Thinking Level. DeepSeek V4.1 Flash moves +386 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
Kimi K3.1 Pro (max) 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 Kimi K3.1 Pro (max) ahead, with a 5.7-point lead on that metric. The weight beside each metric is its share of the Writing Score.
Consistency Across Drafts
| Kimi K3.1 Pro (max) | DeepSeek V4.1 Flash (max) | |
|---|---|---|
| Score spread across drafts (±) | 1.65 | 1.30 |
| Lowest script score | 80.4 Script 7 | 79.7 Script 10 |
| Highest script score | 85.5 Script 9 | 82.4 Script 7 |
| Range across scripts | 5.1 | 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 Kimi K3.1 Pro (max) minus DeepSeek V4.1 Flash (max), and the higher score is in bold.
| Script | Kimi K3.1 Pro (max) | DeepSeek V4.1 Flash (max) | Gap |
|---|---|---|---|
| Script 1 opinion / warning explainer | 81.3 | 80.8 | +0.5 |
| Script 2 news-analysis / skeptical explainer | 83.2 | 81.2 | +2.0 |
| Script 3 personal roadmap / opinion | 81.9 | 81.2 | +0.7 |
| Script 4 short explainer | 82.0 | 80.1 | +1.9 |
| Script 5 news-analysis / opinion explainer | 84.2 | 81.1 | +3.1 |
| Script 6 founder announcement / personal origin story | 83.0 | 80.8 | +2.2 |
| Script 7 personal technical walkthrough / agentic workflow case study | 80.4 | 82.4 | -2.0 |
| Script 8 product release announcement / personal observation | 82.1 | 80.7 | +1.4 |
| Script 9 career guide / hiring analysis | 85.5 | 82.2 | +3.3 |
| Script 10 engineering process walkthrough / presentation adaptation | 81.3 | 79.7 | +1.6 |
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