Towards AITowards AIToneBench

Thinking Levels · Anthropic

Claude Opus 4.8: Writing Quality by Reasoning Effort

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

This page compares Claude Opus 4.8 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 Opus 4.8 ranks #19 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 Opus 4.8

Max effort lifts Claude Opus 4.8 by a clear margin, and it charges for it. Max takes the model from #59 to #39, 137 Elo above the run with no effort flag (high), and the two ranges never touch. The price climbs with it: 6.4 times as much per script, and about 9.8 minutes instead of 1.4.

Recommended Setting

If you're stuck on Claude Opus 4.8, use max. The gain is real, and the board is confident about it. For anything new, though, I'd skip this ladder. Claude Opus 5.5 (low) ranks far above max at #10, costs $0.243 a script against $1.23, and comes back in about 1.5 minutes. The newer Opus at its cheapest setting beats the older one at its most expensive.

Every Setting on the Chart

Each point is one effort setting of Claude Opus 4.8, 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)1789 ±40-79.3$0.1931.4 min#59
max1926 ±35+13780.7$1.239.8 min#39

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.