Gemini 2.5 Flash Lite Max Thinking (2025-06-17)
Parameters
-
Context Length
1,048.576K
Modality
Multimodal
Architecture
Dense
License
Proprietary
Release Date
17 Jun 2025
Knowledge Cutoff
-
Technical Specifications
Attention Structure
Multi-Head Attention
Hidden Dimension Size
-
Number of Layers
-
Attention Heads
-
Key-Value Heads
-
Activation Function
-
Normalization
-
Position Embedding
Absolute Position Embedding
Gemini 2.5 Flash Lite Max Thinking (2025-06-17)
Cost-effective Gemini 2.5 Lite with max thinking capabilities. Fair coding (66.41 LiveBench Coding) and mathematics (61.04) performance at minimal cost. June 2025 release. Best for budget-conscious applications requiring basic reasoning transparency and high throughput.
About Gemini 2.5
Google's advanced multimodal models with native understanding of text, images, audio, and video. Features massive context windows up to 2.1M tokens, max thinking modes for complex reasoning, and optimized variants for different performance/cost tradeoffs. Includes Pro, Flash, and Flash Lite variants with configurable thinking capabilities for transparent reasoning.
Other Gemini 2.5 Models
Evaluation Benchmarks
Rank
#63
| Benchmark | Score | Rank |
|---|---|---|
Data Analysis LiveBench Data Analysis | 0.67 | 30 |
Coding LiveBench Coding | 0.66 | 39 |
Reasoning LiveBench Reasoning | 0.43 | 39 |
Mathematics LiveBench Mathematics | 0.61 | 42 |
Agentic Coding LiveBench Agentic | 0.05 | 45 |
Rankings
Overall Rank
#63
Coding Rank
#42