Thinking Levels · OpenAI
Last updated , from board data generated at 17:52 UTC.
This page compares GPT-6 Astra 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, GPT-6 Astra ranks #13 of 87 models through its best setting. The other ranks on this page are configuration ranks: one setting's place among all 151 configurations.
Max effort lifts GPT-6 Astra clearly, but almost all of the gain is length. Max lands 195 Elo above the run with no effort flag (medium), and the ranges don't overlap. In the scores, length adherence does nearly all the moving, while voice and writing stay flat. That fix isn't cheap: 4.4 times the price, and about 9.2 minutes a script instead of 1.5.
I wouldn't pick Astra for scripts at either setting. If you're already on it, max does give you scripts that fit the target length, and that's worth something if you hate trimming. But GPT-6 Sol (max) ranks above Astra at max, with ranges that don't overlap, for $0.126 a script. That's less than Astra costs with no flag at all, and it comes back in about 2.5 minutes. Astra may well earn its price on other work. For writing, GPT-6 Sol is the one I'd use.
Each point is one effort setting of GPT-6 Astra, 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 | Configuration Rank |
|---|---|---|---|---|---|---|
| medium (provider default) | 1918 ±36 | - | 80.7 | $0.262 | 1.5 min | #41 |
| max | 2113 ±44 | +195 | 82.3 | $1.15 | 9.2 min | #27 |
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 OpenAI family page lists every OpenAI model side by side.