Towards AITowards AIToneBench

Thinking Levels · Anthropic

Claude Fable 5.1: Writing Quality by Reasoning Effort

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

This page compares Claude Fable 5.1 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, Claude Fable 5.1 ranks #4 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 Claude Fable 5.1

Max effort gives Claude Fable 5.1 a clear gain, and an expensive one. With no effort flag (high), it sits at #14. Max comes out 203 Elo ahead at #7, and the two ranges don't overlap, so the board is confident about that order. Meanwhile the price goes from $1.85 to $3.56 a script, and the wait from about 6.3 minutes to 12.3.

Recommended Setting

If you're on Claude Fable 5.1, run max. The gain is real, and it costs 1.9 times as much per script. Better still, move to the newer Fable: Claude Fable 5.2 (high) ranks above this model at max, with overlapping ranges, for $1.22 a script, less than Claude Fable 5.1 costs with no flag.

But I'd question running Fable for scripts at all. Claude Opus 5.5 (low) ranks above Claude Fable 5.1 with no flag, with a clear gap between the ranges. Against Claude Fable 5.1 at max, Opus trails by 60 Elo on the point estimates, and the ranges overlap, though overlap alone doesn't test their difference. Opus costs $0.243 a script and takes about 1.5 minutes, and Claude Fable 5.1 at max costs 14.7 times as much. Fable may well earn that price on other work. On scripts, the cheapest Claude Opus 5.5 setting is already the one I'd pick.

Every Setting on the Chart

Each point is one effort setting of Claude Fable 5.1, 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 / ScriptConfiguration Rank
high (provider default)2282 ±62-83.4$1.856.3 min#14
max2485 ±38+20384.5$3.5612.3 min#7

Other Anthropic 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 Anthropic family page lists every Anthropic model side by side.