Towards AITowards AIToneBench

Thinking Levels · OpenAI

GPT-6 Luna: Writing Quality by Reasoning Effort

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

This page compares GPT-6 Luna at 3 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, GPT-6 Luna ranks #33 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 GPT-6 Luna

Effort lifts GPT-6 Luna a little, with the highest rating at max. Each step overlaps the next, but the two ends, max and the run with no effort flag (medium), 91 Elo apart, have ranges that just miss each other. Every setting costs a fraction of a cent per script, so the real cost of max is the wait, about 1.3 minutes instead of 0.5.

Recommended Setting

If you're on GPT-6 Luna, set it to max. It has the top score here, mostly from better YouTube best-practices and cue scores, and it still costs a fraction of a cent. Voice stays weak at every setting, and thinking harder doesn't move it. If you want cheap OpenAI scripts, GPT-6.1 Terra (low) ranks far above all 3 settings for $0.027 a script, back in about 0.5 minutes.

Every Setting on the Chart

Each point is one effort setting of GPT-6 Luna, 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 / ScriptConfiguration Rank
medium (provider default)1571 ±52-77.0$0.00260.5 min#80
high1604 ±50-77.4$0.00280.6 min#75
max1662 ±38+5878.2$0.00461.3 min#70

The 95% Writing Elo ranges overlap: GPT-6 Luna (high) runs from 1547 to 1647, and GPT-6 Luna (max) from 1625 to 1700.

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