Gemini 3 Flash Preview
Parameters
Undisclosed
Context Length
1.05M
Modality
Multimodal
Architecture
Undisclosed
License
Proprietary
Release Date
8 Jan 2026
Knowledge Cutoff
Jan 2025
API Pricing (per 1M)
Input: $0.50 · Output: $3.00
Evaluation Benchmarks
Rank
#62
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.76 | 5 |
StackUnseen | 0.83 | 13 |
Graduate-Level QA | 0.904 | 23 |
General Text | low 1458 Standard 1474 | 46 28 |
Agent Arena | -12.11 | 50 |
Web Development | low 1383 Standard 1438 | 75 58 |
Intelligence Index | auto 0.26 Standard 0.18 | 94 161 |
Rankings
Overall Rank
#62
Coding Rank
#67
About Gemini 3 Flash Preview
Gemini 3 Flash Preview is a high-speed multimodal model from Google DeepMind optimized for low latency and high-concurrency production tasks. It supports configurable reasoning depth and native video/audio processing over a 1M token context window.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
Resources
About Gemini 3
Google's latest generation multimodal models with breakthrough performance across coding, mathematics, reasoning, and language understanding. Features ultra-large context windows, native multimodal processing, and thinking modes with minimal latency overhead. Available in Pro and Flash variants optimized for different workloads, with preview versions showing state-of-the-art results on multiple benchmarks.