Head to head
Gemini 3.8 Flash vs GPT-6 Luna
Which is better, Gemini 3.8 Flash or GPT-6 Luna?
Gemini 3.8 Flash finishes ahead of GPT-6 Luna on the index, 87.9 to 84.9. It is the stronger of the two on Craft, while GPT-6 Luna still leads on Speed and Value. Both are scored on the same rubric, in the same week, and neither placing is sponsored.
Updated
Gemini 3.8 Flash
09 of 73
87.9
Google's smartest Flash yet, eighth on the arena, and still free to start on.
GPT-6 Luna
22 of 73
84.9
The cheap end of GPT-6, and the model free ChatGPT users now talk to.
The four scores, side by side
| Score | Gemini 3.8 Flash | GPT-6 Luna | Difference |
|---|---|---|---|
| Craft | 88 | 80 | +8 |
| Speed | 90 | 93 | +3 |
| Control | 86 | 85 | +1 |
| Value | 88 | 94 | +6 |
| Index score | 87.9 | 84.9 | +3.0 |
Which to pick
Pick Gemini 3.8 Flash unless Speed and Value is what decides it for you, which is exactly where GPT-6 Luna is the better answer.
Gemini 3.8 Flash
Gemini 3.8 Flash went generally available on 2 September and replaced the short-lived 3.7 Flash within weeks. It reads text, images, video, audio and PDFs, takes a million tokens of context, and sits eighth on the arena leaderboard, ahead of many full-price flagships. The free tier covers it, and the paid price is introductory until the end of the year, when it doubles. Its benchmark scores trail its human-preference rating, which is worth knowing before you trust it with long agent work.
Where it shines
- Eighth on the arena leaderboard at Flash prices
- Native video, audio and PDF input
- The free tier covers it, so prototyping costs nothing
GPT-6 Luna
Luna is OpenAI's efficiency tier, priced at ten cents per million input tokens with a million-token window and the same structured-output discipline as the rest of the family. Since 7 October it is also what free ChatGPT users get, so for a great many people this model is now what ChatGPT means. It costs half of what GPT-5.6 Luna did for slightly better benchmark scores. Deep reasoning is not its job.
Where it shines
- Ten cents per million input tokens, and a cent for cached input
- The model behind free ChatGPT since October
- Same tool-calling and structured-output behaviour as its larger siblings