Towards AITowards AIToneBench

Model Scorecard

DeepSeek V4.1 Flash 1017 (high)

DeepSeek · open weights

DeepSeek V4.1 Flash 1017 ranks #15 of 87 models on the November 2026 ToneBench board through its best configuration, DeepSeek V4.1 Flash 1017 (max). This setting, DeepSeek V4.1 Flash 1017 (high), is #34 of 151 configurations, with a Writing Score of 81.1/100 and a Writing Elo of 1974. One script costs $0.0095 at API list price.

Last updated , from board data generated at 17:52 UTC.

Rank, scores, the nine metrics, the 10 reference scripts, cost and setup for one configuration (a model at one reasoning setting). Key Results sums it up; the section links below it jump to the detail.

Model Rank ?
#15 of 87 modelsthrough DeepSeek V4.1 Flash 1017 (max); this setting is #34 of 151 configurations
Writing Score ?
81.1 out of 100
Writing Elo ?
1974 95% range 1929 to 2021
Cost per Script
$0.0095 at API list price

Key Results

Louis's PickI'd stay with this one: DeepSeek V4.1 Flash 1017 (max) is the strongest DeepSeek V4.1 Flash 1017 setting, but their Elo ranges overlap, and it costs under a cent more per script.

More Context Behind These Results

Writing Elo comes from comparing its average on each script with every other configuration's average on that same script; a gap smaller than the draft-to-draft variation counts as a draw (what the ranges can and cannot show).

On Writing Craft & Clarity, its best-ranked metric, its sentences need less smoothing than the typical configuration's. Visual Cue Quality ranks in the bottom half (90th of 151 configurations), so expect to add most of the visual cues by hand.

The script format moves its score. If most of your scripts look like its best or weakest format, that result is a better guide than the average.

Its drafts vary little, so the first draft is usually close to the next one.

It outranks 85 configurations that cost at least 50% more.

Among open-weight models, DeepSeek V4.1 Flash 1017 is 4th of 34. This setting is 5th of 43 open-weight configurations. That is one of the strongest open-weight results on this board.

Lab
DeepSeek 1st of 5 modelsthis setting 2nd of 11 configurations
Weights
Open 4th of 34 modelsthis setting 5th of 43 configurations
Consistency
± 1.8 steadier than most
Average Tokens
25.9k input + output
Time per Script
0.9 min average, retries included
Highest-Ranked in This LabDeepSeek V4.1 Flash 1017 (max) ranks highest of the DeepSeek configurations by Writing Elo, with a Writing Score +0.5 against this configuration, for under a cent more per script. Their Elo ranges overlap.

All Settings of DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is also on the board at other effort settings, and DeepSeek V4.1 Flash 1017 (max) ranks higher, though their Elo ranges overlap. The thinking-level page for DeepSeek V4.1 Flash 1017 charts how quality, cost and time change with the setting.

SettingConfiguration RankWriting ScoreWriting EloCost / ScriptTime / Script
max#3081.62024$0.0141.3 min
high this page#3481.11974$0.00950.9 min

Skill Profile Across the Nine Metrics

Each corner is one metric on a 0 to 100 scale; the further out, the higher the score. A corner outside the dashed line beats the board median. Hover or tap a point for its exact score, and a metric name for what it rewards.

50Tone?Craft?Substance?Flow?YouTube?Hook?Length?Slop?Cues?
DeepSeek V4.1 Flash 1017 (high)Board medianBoard best per metricMax possible (100)

Scores by Metric

Nine metrics, each scored 0 to 100 and weighted into the Writing Score; the weight sits under each name. Rank is out of all 151 ranked configurations.

Score colors:Strong: 82 and upMiddle: 65 to 81.9Weak: under 65
This modelBoard best (upper line)Board median (lower line)±: spread between drafts?: what the metric rewards
Tone & Voice Match ?19% weight · +5.5 vs median
board best 82.8 · Claude Opus 5.5 (max effort)79.6± 1.3 · 21stboard median 74.0
Writing Craft & Clarity ?13% weight · +4.4 vs median
board best 83.2 · Claude Opus 5.5 (xhigh)79.5± 1.1 · 20thboard median 75.0
Substance, Accuracy & Value ?15% weight · +0.4 vs median
board best 88.4 · Claude Opus 5.5 (xhigh)82.2± 2.4 · 73rdboard median 81.8
Continuity & Emotion ?14% weight · +3.4 vs median
board best 85.7 · Claude Opus 5.5 (max effort)80.9± 1.1 · 31stboard median 77.5
YouTube Best Practices ?12% weight · +3.7 vs median
board best 84.5 · Claude Fable 5.2 (max effort)80.0± 2.2 · 31stboard median 76.4
Hook Strength ?10% weight · +1.6 vs median
board best 84.0 · Claude Fable 5.2 (xhigh)81.2± 2.4 · 45thboard median 79.6
Length Adherence ?8% weight · +4.1 vs median
board best 99.0 · Claude Fable 5.2 (xhigh)88.8± 6.9 · 55thboard median 84.8
Slop Score ?5% weight · +2.9 vs median
board best 89.0 · GPT-6 Sol (medium)84.2± 1.4 · 44thboard median 81.3
Visual Cue Quality ?4% weight · -1.3 vs median
board best 85.9 · Claude Opus 5.5 (max effort)73.4± 4.8 · 90thboard median 74.8

Scores by Reference Script

Every ranked configuration writes five drafts for each of the same 10 briefs, and each score is the mean of those drafts. The rank and board median compare it with every configuration on that script, which separates a weak result from a hard script. The result on the format closest to your own work is the most relevant.

Script 1
opinion / warning explainer
80.8
out of 100
37th of 151 configurations on this script · board median 77.2
Script 2
news-analysis / skeptical explainer
80.8
out of 100
44th of 151 configurations on this script · board median 78.4
Script 3
personal roadmap / opinion
80.8
out of 100
42nd of 151 configurations on this script · board median 77.2
Script 4
short explainer
79.6
out of 100
43rd of 151 configurations on this script · board median 75.7
Script 5
news-analysis / opinion explainer
81.8
out of 100
33rd of 151 configurations on this script · board median 78.0
Script 6
founder announcement / personal origin story
80.8
out of 100
59th of 151 configurations on this script · board median 79.2
Script 7
personal technical walkthrough / agentic workflow case study
82.4
out of 100
26th of 151 configurations on this script · board median 77.9
Script 8
product release announcement / personal observation
81.8
out of 100
31st of 151 configurations on this script · board median 79.0
Script 9
career guide / hiring analysis
83.0
out of 100
38th of 151 configurations on this script · board median 79.3
Script 10
engineering process walkthrough / presentation adaptation
79.1
out of 100
41st of 151 configurations on this script · board median 75.0

Consistency Between Drafts

Every score on this page is the mean of 5 drafts per script. The ± is the standard deviation between those drafts: the larger it is, the more two drafts of the same script can differ.

Compared with the typical model, it varies most on Visual Cue Quality: ± 4.8 between drafts against ± 2.9, so two drafts of the same script can score quite differently there.

Consistency by Metric
MetricThis modelBoard medianVerdict
Tone & Voice Match ?79.6 ± 1.3± 1.9typical
Writing Craft & Clarity ?79.5 ± 1.1± 1.5typical
Substance, Accuracy & Value ?82.2 ± 2.4± 2.1typical
Continuity & Emotion ?80.9 ± 1.1± 1.5typical
YouTube Best Practices ?80.0 ± 2.2± 2.4typical
Hook Strength ?81.2 ± 2.4± 2.7typical
Length Adherence ?88.8 ± 6.9± 6.6typical
Slop Score ?84.2 ± 1.4± 1.6typical
Visual Cue Quality ?73.4 ± 4.8± 2.9more variable than most

Cost, Time and Tokens per Script

Logged on every run; none of these figures affects the Writing Score. Time is the average time to one accepted script, retries included. Cost is one script at the API list price.

Time per Script
0.9 minfaster than the board median of 1.5 min
Prompt tokens in
13.5kstyle guide + brief + research packet
Tokens Out
12.5kscript + any reasoning tokens
Cost per Script
$0.0095measured from actual billed tokens; varies ± 0.005 between drafts
List Price Used
$0.15 / $0.6input / output, per million tokens

Scores by Judge

Four judges score the same 50 stored drafts blind against the same rubric: three LLM judges from three labs, plus Jev, a typed judge from TypeSafe that rates each metric on five described quality levels. No single judge's taste decides the result. The Writing Score of 81.1 combines their scores with the parts computed in code (Length Adherence and half of the Slop Score). The highest and lowest judge are 11.9 points apart on its Writing Score. That is close to the board median of 13.4. Each judge also has its own scale, so every card shows that judge's score against its average across the board. How the panel works.

Claude Opus 5.5 (medium)
Anthropic
77.7
+9.1 against its board average of 68.7
GLM 5.3 Flash
Z.ai
88.4
+5.5 against its board average of 82.9
GPT-6.1 Sol (medium)
OpenAI
76.5
+4.6 against its board average of 71.9
Jev 1.13
TypeSafe
81.7
+7.7 against its board average of 74.0

Evaluation Setup

How this exact configuration was run and judged: route, model ID, dates, sampling and prompt.

Frequently Asked Questions

How Good Is DeepSeek V4.1 Flash 1017 (high) at Writing?

DeepSeek V4.1 Flash 1017 ranks #15 of 87 models on ToneBench through its best configuration, DeepSeek V4.1 Flash 1017 (max). This configuration is #34 of 151 configurations, in the upper third of the board, with a Writing Elo of 1974 and a Writing Score of 81.1/100. The ranks come from full YouTube scripts written in the voice of Louis-François Bouchard and judged blind, with the channel's finished script as the reference. The benchmark measures long-form scripted writing, so the result does not carry over to every kind of text.

Is DeepSeek V4.1 Flash 1017 (high) the Best DeepSeek Model for Writing?

DeepSeek V4.1 Flash 1017 is the top DeepSeek model, #15 of 87 models, through DeepSeek V4.1 Flash 1017 (max). This setting is 2nd of 11 DeepSeek configurations, about 50 Elo behind it, inside the overlap of their Elo ranges.

Is DeepSeek V4.1 Flash 1017 (high) Good Value for the Money?

It costs about $0.0095 per script. That is good value: no configuration at least 15% cheaper ranks higher.

What Are the Strengths and Weaknesses of DeepSeek V4.1 Flash 1017 (high)?

Its best-ranked metric is Writing Craft & Clarity (79.5, 20th of 151 configurations, +4.4 against the board median), and its lowest-ranked is Visual Cue Quality (73.4, 90th of 151, -1.3). The Scores by Metric section shows the board median and the board's best for each one.

How Was DeepSeek V4.1 Flash 1017 (high) Evaluated?

It was run through OpenRouter, with the exact model/route ID deepseek/deepseek-v4.1-flash-1017 at reasoning effort high, first run on 2026-10-17. It wrote each script 5 times with the provider's default sampling and no fine-tuning. The Evaluation Setup section and the methodology page have the details.

Does DeepSeek V4.1 Flash 1017 (high) Have Open Weights?

Yes. Its weights are public, so it can be downloaded and run on your own hardware. Check the license if you need open source in the strict sense. Among open-weight configurations it is 5th of 43 for writing.

← All models   ← Leaderboard