Towards AITowards AIToneBench

Thinking Levels · Google

Gemini 3.6 Flash: Writing Quality by Reasoning Effort

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

This page compares Gemini 3.6 Flash 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, Gemini 3.6 Flash ranks #61 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 Gemini 3.6 Flash

High thinking hardly changes Gemini 3.6 Flash. High and the medium thinking you get with no flag end up 2 Elo apart, with ranges that overlap almost entirely. The model already thinks a lot with no flag, so high adds only a little more reasoning, and the cost barely moves: $0.060 a script against $0.052.

Recommended Setting

Leave it on medium thinking. High costs a little more, takes a little longer, and barely changes Writing Elo. The one thing Gemini 3.6 Flash does well at either setting is length: its scripts land closer to the target than every other Gemini Flash ladder here except Gemini 3.5 Flash. For new work, though, Gemini 2.5 Pro (dynamic thinking) ranks above both settings, with a clear gap between the ranges, for about the same price at $0.067 a script.

Every Setting on the Chart

Each point is one effort setting of Gemini 3.6 Flash, 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 thinking (provider default)1010 ±45-69.3$0.0520.9 min8,221#119
high1008 ±45-269.2$0.0601.1 min10,372#120

The 95% Writing Elo ranges overlap: Gemini 3.6 Flash (medium thinking) runs from 970 to 1059, and Gemini 3.6 Flash (high thinking) from 959 to 1049.

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