Thinking Levels · Google
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.
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.
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.
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.
On a small screen, Table lists the same numbers as rows.
| Setting | Writing Elo | Step | Writing Score | Cost / Script | Time / Script | Reasoning Tokens | Configuration Rank |
|---|---|---|---|---|---|---|---|
| low | 1052 ±42 | - | 70.1 | $0.105 | 0.8 min | 4,022 | #113 |
| high | 1102 ±42 | +50 | 71.0 | $0.148 | 1.2 min | 7,349 | #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.
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.