Towards AITowards AIToneBench

Model Scorecard

Muse Spark 1.3 (medium)

Meta · proprietary

Muse Spark 1.3 ranks #45 of 87 models on the November 2026 ToneBench board through its best configuration, Muse Spark 1.3 (high). This setting, Muse Spark 1.3 (medium), is #95 of 151 configurations, with a Writing Score of 75.4/100 and a Writing Elo of 1451. One script costs $0.038 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 ?
#45 of 87 modelsthrough Muse Spark 1.3 (high); this setting is #95 of 151 configurations
Writing Score ?
75.4 out of 100
Writing Elo ?
1451 95% range 1399 to 1494
Cost per Script
$0.038 at API list price

Key Results

Louis's PickI'd stay with this one: Muse Spark 1.3 (high) is the strongest Muse Spark 1.3 setting, but their Elo ranges overlap, and it costs about 1 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).

Visual Cue Quality ranks in the bottom half (117th of 151 configurations), so expect to add most of the visual cues by hand.

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

It outranks 16 configurations that cost at least 50% more.

Among proprietary models, Muse Spark 1.3 is 35th of 53. This setting is 80th of 108 proprietary configurations. The best open-weight configuration, GLM-5.3 (max) at configuration #22, outranks it.

Lab
Meta 2nd of 4 modelsthis setting 5th of 7 configurations
Weights
Proprietary 35th of 53 modelsthis setting 80th of 108 configurations
Consistency
± 2.9 typical spread
Average Tokens
18.2k input + output
Time per Script
1.1 min average, retries included
Highest-Ranked in This LabMuse Wonder (max) ranks highest of the Meta configurations by Writing Elo, with a Writing Score +5.2 against this configuration, for about 27 cents more per script.

All Settings of Muse Spark 1.3

Muse Spark 1.3 is also on the board at other effort settings, and Muse Spark 1.3 (high) ranks higher, though their Elo ranges overlap. The thinking-level page for Muse Spark 1.3 charts how quality, cost and time change with the setting.

SettingConfiguration RankWriting ScoreWriting EloCost / ScriptTime / Script
high#9475.51455$0.0481.5 min
medium this page#9575.41451$0.0381.1 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?
Muse Spark 1.3 (medium)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 · -0.6 vs median
board best 82.8 · Claude Opus 5.5 (max effort)73.4± 2.0 · 83rdboard median 74.0
Writing Craft & Clarity ?13% weight · -2.4 vs median
board best 83.2 · Claude Opus 5.5 (xhigh)72.7± 1.5 · 90thboard median 75.0
Substance, Accuracy & Value ?15% weight · -1.3 vs median
board best 88.4 · Claude Opus 5.5 (xhigh)80.5± 2.5 · 86thboard median 81.8
Continuity & Emotion ?14% weight · -1.0 vs median
board best 85.7 · Claude Opus 5.5 (max effort)76.5± 1.9 · 88thboard median 77.5
YouTube Best Practices ?12% weight · +1.5 vs median
board best 84.5 · Claude Fable 5.2 (max effort)77.9± 2.5 · 58thboard median 76.4
Hook Strength ?10% weight · -1.8 vs median
board best 84.0 · Claude Fable 5.2 (xhigh)77.8± 2.7 · 98thboard median 79.6
Length Adherence ?8% weight · -16.2 vs median
board best 99.0 · Claude Fable 5.2 (xhigh)68.5± 13.0 · 114thboard median 84.8
Slop Score ?5% weight · -0.8 vs median
board best 89.0 · GPT-6 Sol (medium)80.5± 1.4 · 90thboard median 81.3
Visual Cue Quality ?4% weight · -9.3 vs median
board best 85.9 · Claude Opus 5.5 (max effort)65.4± 6.7 · 117thboard 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
74.8
out of 100
96th of 151 configurations on this script · board median 77.2
Script 2
news-analysis / skeptical explainer
76.9
out of 100
92nd of 151 configurations on this script · board median 78.4
Script 3
personal roadmap / opinion
75.6
out of 100
92nd of 151 configurations on this script · board median 77.2
Script 4
short explainer
77.0
out of 100
68th of 151 configurations on this script · board median 75.7
Script 5
news-analysis / opinion explainer
71.4
out of 100
107th of 151 configurations on this script · board median 78.0
Script 6
founder announcement / personal origin story
78.5
out of 100
87th of 151 configurations on this script · board median 79.2
Script 7
personal technical walkthrough / agentic workflow case study
74.9
out of 100
96th of 151 configurations on this script · board median 77.9
Script 8
product release announcement / personal observation
75.5
out of 100
105th of 151 configurations on this script · board median 79.0
Script 9
career guide / hiring analysis
77.2
out of 100
92nd of 151 configurations on this script · board median 79.3
Script 10
engineering process walkthrough / presentation adaptation
72.6
out of 100
93rd 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: ± 6.7 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 ?73.4 ± 2.0± 1.9typical
Writing Craft & Clarity ?72.7 ± 1.5± 1.5typical
Substance, Accuracy & Value ?80.5 ± 2.5± 2.1typical
Continuity & Emotion ?76.5 ± 1.9± 1.5typical
YouTube Best Practices ?77.9 ± 2.5± 2.4typical
Hook Strength ?77.8 ± 2.7± 2.7typical
Length Adherence ?68.5 ± 13.0± 6.6more variable than most
Slop Score ?80.5 ± 1.4± 1.6typical
Visual Cue Quality ?65.4 ± 6.7± 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
1.1 minfaster than the board median of 1.5 min
Prompt tokens in
13.2kstyle guide + brief + research packet
Tokens Out
5.0kscript + any reasoning tokens
Cost per Script
$0.038measured from actual billed tokens; varies ± 0.008 between drafts
List Price Used
$1.25 / $4.25input / 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 75.4 combines their scores with the parts computed in code (Length Adherence and half of the Slop Score). The highest and lowest judge are 14.2 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
69.8
+1.1 against its board average of 68.7
GLM 5.3 Flash
Z.ai
84.0
+1.1 against its board average of 82.9
GPT-6.1 Sol (medium)
OpenAI
71.0
-0.9 against its board average of 71.9
Jev 1.13
TypeSafe
76.9
+2.9 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 Muse Spark 1.3 (medium) at Writing?

Muse Spark 1.3 ranks #45 of 87 models on ToneBench through its best configuration, Muse Spark 1.3 (high). This configuration is #95 of 151 configurations, in the middle third of the board, with a Writing Elo of 1451 and a Writing Score of 75.4/100. 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 Muse Spark 1.3 (medium) the Best Meta Model for Writing?

No. Muse Spark 1.3 is 2nd of 4 Meta models. The top one is Muse Wonder, through Muse Wonder (max), about 479 Elo ahead of this setting.

Is Muse Spark 1.3 (medium) Good Value for the Money?

It costs about $0.038 per script. GPT-6 Luna (medium) ranks higher and costs less.

What Are the Strengths and Weaknesses of Muse Spark 1.3 (medium)?

Its best-ranked metric is YouTube Best Practices (77.9, 58th of 151 configurations, +1.5 against the board median), and its lowest-ranked is Visual Cue Quality (65.4, 117th of 151, -9.3). The Scores by Metric section shows the board median and the board's best for each one.

How Was Muse Spark 1.3 (medium) Evaluated?

It was run through OpenRouter, with the exact model/route ID meta/muse-spark-1.3, first run on 2026-10-08. 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 Muse Spark 1.3 (medium) Have Open Weights?

No. It is a proprietary model: its weights are not public. Among proprietary configurations it is 80th of 108 for writing.

← All models   ← Leaderboard