Parameters
-
Context Length
1,048.576K
Modality
Multimodal
Architecture
Dense
License
Proprietary
Release Date
8 Jan 2026
Knowledge Cutoff
-
Attention Structure
Multi-Head Attention
Hidden Dimension Size
-
Number of Layers
-
Attention Heads
-
Key-Value Heads
-
Activation Function
-
Normalization
-
Position Embedding
Absolute Position Embedding
Google's latest high-performance Gemini model with exceptional multimodal capabilities. Outstanding performance across all benchmarks with top scores in reasoning (74.55), coding (73.90), mathematics (84.17), and language (84.56). Excellent web development results (Elo 1450). Features ultra-large context window and native understanding of text, images, audio, and video. Ideal for complex multimodal tasks.
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.
Rank
#6
| Benchmark | Score | Rank |
|---|---|---|
Agentic Coding LiveBench Agentic | 0.69 | 🥉 3 |
StackUnseen ProLLM Stack Unseen | 0.86 | 4 |
Web Development WebDev Arena | 1450 | 6 |
Mathematics LiveBench Mathematics | 0.80 | 10 |
Reasoning LiveBench Reasoning | 0.75 | 14 |
Coding LiveBench Coding | 0.74 | 20 |
Overall Rank
#6
Coding Rank
#3 🥉