Towards AITowards AIToneBench

Thinking Levels · Google

Gemini 3.1 Pro: Writing Quality by Reasoning Effort

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

This page compares Gemini 3.1 Pro 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 3.1 Pro ranks #55 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 3.1 Pro

High thinking gives Gemini 3.1 Pro a small lead over low on Writing Elo. The model ran at low and high thinking only, and high comes out 50 Elo ahead, enough to win about 57% of script comparisons, but the two ranges overlap; that alone doesn't settle their order. It costs 1.4 times as much per script and takes about 1.2 minutes instead of 0.8.

Recommended Setting

I'd run it at high. It leads on the point estimate, scripts land closer to the target length, and the cue and YouTube best-practices scores tick up a little too. At $0.148 a script, that's an easy trade if you're already on it.

For a new project, I'd look elsewhere. Even at high, Gemini 3.1 Pro sits at #110 on the board, and Gemini 2.5 Pro (dynamic thinking) ranks just above it for $0.067 a script. The ranges overlap; overlap alone doesn't settle their order, but the older model gets there for less money and less waiting.

Every Setting on the Chart

Each point is one effort setting of Gemini 3.1 Pro, 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.

All Effort Settings, Step by Step

Score colors:82 and up65 to 81.9under 65
SettingWriting EloStepWriting ScoreCost / ScriptTime / ScriptReasoning TokensConfiguration Rank
low1052 ±42-70.1$0.1050.8 min4,022#113
high1102 ±42+5071.0$0.1481.2 min7,349#110

The 95% Writing Elo ranges overlap: Gemini 3.1 Pro (low thinking) runs from 1011 to 1095, and Gemini 3.1 Pro (high thinking) from 1058 to 1142.

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 previous explicit setting. 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.