Models · Google DeepMind
Gemini 3.5 Flash-Lite
Google DeepMind's Gemini model, released 21 Jul 2026.
Top three for
No task yet.
Evidence
Independently tested. 14 independent results so far.
Cost
$2.35 per 1,000 typical requests, if you use it directly.
Reads at once
1,573 pages of about 500 words.
Where it ranks, task by task
Its place on each task's score, among the models we compare that have enough results to score.
| Task | Position | Task score |
|---|---|---|
| Best AI for health questions | 10th of 14 | 36 |
| Best AI for studying and homework | 11th of 12 | 37 |
| Best AI for maths and science | 11th of 12 | 36 |
| Best AI for planning and personal admin | 12th of 14 | 32 |
| Best AI for translation and languages | 12th of 14 | 38 |
| Best AI for writing | 12th of 14 | 20 |
| Best AI for documents, PDFs and notes | 12th of 13 | 24 |
| Best AI for CVs, job applications and interviews | 13th of 14 | 16 |
Test results
Every test we use that has a result for this exact version.
Details
- Maker
- Google DeepMind
- Released
- 21 Jul 2026
- Status
- Current
- Name checked
- Not yet confirmed with the maker