Towards AITowards AIToneBench

Thinking Levels · Meta

Muse Spark 1.3: Writing Quality by Reasoning Effort

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

This page compares Muse Spark 1.3 at 2 reasoning-effort settings, each tested on the same 10 scripts: the Writing Score (the 0 to 100 consensus of the judges and code), the Writing Elo (a rating from pairwise comparisons of those scores), and the cost and time of each setting. As a model, Muse Spark 1.3 ranks #45 of 87 models through its best setting. The other ranks on this page are configuration ranks: one setting's place among all 151 configurations.

What More Effort Changes for Muse Spark 1.3

High thinking gives Muse Spark 1.3 a small lead on Writing Elo. Muse Spark 1.3 (high) scores 4 Elo above Muse Spark 1.3 (medium), which is nothing on this scale, and the two ranges overlap. Luckily, little is riding on it: $0.048 a script against $0.038, and the wait barely changes.

Recommended Setting

Either one is fine, and I'd lean toward leaving the flag off. You save a little on every script, and the Elo lead is small. Just don't expect thinking to fix what holds this model back. Both settings score about the same on every metric, and visual cues and length adherence are the two weakest at both. If length is your problem, thinking harder won't solve it, and you'll still be trimming or padding scripts by hand.

Every Setting on the Chart

Each point is one effort setting of Muse Spark 1.3, joined from the lowest setting to the highest. Higher and further left is better: a higher score for less money or less time.

How to Use the Chart
  • A hollow marker is the provider default: the level the provider applies when the request sets no effort level.
  • The tabs choose the score on the vertical axis, X axis switches between cost and time, and Table lists the same numbers as rows.
  • Select a point for its numbers and a link to its scorecard.
Score on the vertical axis
View
X axis

On a small screen, Table lists the same numbers as rows.

Both Effort Settings Compared

Score colors:82 and up65 to 81.9under 65
SettingWriting EloStepWriting ScoreCost / ScriptTime / ScriptReasoning TokensConfiguration Rank
medium (provider default)1451 ±48-75.4$0.0381.1 min2,186#95
high1455 ±52+475.5$0.0481.5 min4,623#94

The 95% Writing Elo ranges overlap: Muse Spark 1.3 (medium) runs from 1399 to 1494, and Muse Spark 1.3 (high) from 1401 to 1504.

Other Meta Models by Effort

Writing Elo comes from comparing every pair of models on every script, which puts these settings on the same scale as the leaderboard. Step is the Writing Elo change from the provider default. Cost is one full script at API list prices, and time is the average for one accepted script, retries included. The thinking-levels page covers the other models, and the Meta family page lists every Meta model side by side.