Thinking Levels · Anthropic
Last updated , from board data generated at 17:52 UTC.
This page compares Claude Fable 5 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 ranks #7 of 87 models through its best setting. The other ranks on this page are configuration ranks: one setting's place among all 151 configurations.
Max effort lifts Claude Fable 5 on Writing Elo, by a modest margin. Max lands 95 Elo above the run with no effort flag (high), and the two ranges just overlap, though overlap alone doesn't test their difference. The bill moves more: 2.4 times the price, $3.20 a script, and about 12.5 minutes of waiting instead of 4.9.
Leave the flag off. Max does come out ahead on the point estimate, but paying that much more and waiting that much longer for a modest lead is a bad trade, especially on a model I wouldn't pick for scripts anymore. Claude Fable 5.2 (high) ranks far above both settings here at #5, for $1.22 a script, less than Claude Fable 5 costs with no flag. And Claude Opus 5.5 (low) sits far above both too, at #10, for $0.243 a script. Even without the flag, Claude Fable 5 costs 5.5 times as much as that.
Each point is one effort setting of Claude Fable 5, joined from the lowest setting to the highest. Higher and further left is better: a higher score for less money or less time.
On a small screen, Table lists the same numbers as rows.
| Setting | Writing Elo | Step | Writing Score | Cost / Script | Time / Script | Configuration Rank |
|---|---|---|---|---|---|---|
| high (provider default) | 2070 ±51 | - | 81.9 | $1.34 | 4.9 min | #28 |
| max | 2165 ±58 | +95 | 82.9 | $3.20 | 12.5 min | #17 |
The 95% Writing Elo ranges overlap: Claude Fable 5 (high) runs from 2014 to 2116, and Claude Fable 5 (max effort, Opus 4.8 fallback) from 2102 to 2218.
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.