Google · released Sep 2, 2026
Gemini 3.8 Flash
Gemini 3.8 Flash gives near-flagship answers for a small fraction of the price.
8 weeks oldThinks before answering
- Input price
- $0.75 / M
- Output price
- $3.75 / M
- Context
- 1M tokens
- Longest reply
- 66K
- Reads
- text, image, video, audio, pdf
- Knows up to
- –
Where it shines
- It scores 1498 on text at $0.75 in, $3.75 out.
- It scores 1315 on vision, six points behind Opus 5.5.
- It scores 69.7 on SimpleQA.
Where it struggles
- Its web dev score of 1584 trails Opus 5.5 by 225 points.
Where you can use it
- Gemini appAppIn the model picker for Google AI Pro and Ultra.
- Gemini APIAPI$0.75 in / $3.75 out per million tokens.
- OpenRouterAPIListed as
google/gemini-3.8-flash
How it scores on each job
Scores run 0 to 100 and blend every measure we have for that job. The number after the dot is its rank among the 33 models in the lineup.
The evidence
| Measure | Score | Rank in lineup | Source |
|---|---|---|---|
| Epoch Capabilities Index | 157 | #13 | Epoch AI |
| LMArena text | 1498 | #5 | LMArena |
| LMArena hard prompts | 1509 | #5 | LMArena |
| LMArena instruction following | 1492 | #5 | LMArena |
| LMArena multi-turn | 1503 | #4 | LMArena |
| LMArena creative writing | 1489 | #6 | LMArena |
| LMArena writing & language | 1494 | #5 | LMArena |
| LMArena coding | 1508 | #9 | LMArena |
| LMArena math | 1532 | #3 | LMArena |
| LMArena business & finance | 1479 | #8 | LMArena |
| LMArena legal & government | 1498 | #7 | LMArena |
| LMArena medicine | 1506 | #5 | LMArena |
| WebDev Arena | 1584 | #20 | LMArena |
| Vision Arena | 1315 | #3 | LMArena |
| Agent Arena | #14 | #9 | LMArena |
| GPQA Diamond | 95% | #5 | Epoch AI |
| Humanity's Last Exam | 45% | #5 | Epoch AI |
| FrontierMath | 68% | #19 | Epoch AI |
| SimpleQA Verified | 70% | #7 | Epoch AI |
| ARC-AGI-2 | 89% | #6 | Epoch AI |
Compare it with these
3 months old
Gemini 3.7 Flash
Gemini 3.7 Flash is a cheap, capable Google model that Gemini 3.8 Flash has replaced.
WritingEveryday questions
- Price
- $0.75 in · $3.75 out
- Context
- 1M
8 months old
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is Google's older flagship, and Gemini 4 Argon beats it for less money.
Writing
- Price
- $2 in · $12 out
- Context
- 1M
8 weeks old
Meta
Muse Spark 1.3
Muse Spark 1.3 is Meta's mid-price model and reads documents well for its cost.
Long documentsEveryday questions
- Price
- $1.25 in · $4.25 out
- Context
- 1M