Gemini 3.5 Flash
Google Gemini 3.5 Flash is a Google model for agentic workflows, sub-agent deployment, multi-step tasks, rapid coding loops, and long-horizon work.
Model Overview
Capabilities, design details, and architectural traits
Gemini 3.5 Flash - agentic Flash model
Gemini 3.5 Flash is built for fast, agentic work. It combines frontier-level intelligence with Flash-level speed and scale, and it is positioned for real-world tasks.
| Distinctive trait | What is documented |
|---|---|
| Agentic workflow focus | Designed for the agentic era, with sub-agent deployment, multi-step workflows, and long-horizon tasks. |
| Rapid coding loops | Described as effective for rapid agentic loops, including complex coding cycles and iterations. |
| Multimodal input | Supports text, image, video, audio, and PDF inputs. |
| Tool use | Supports function calling, structured outputs, search as a tool, code execution, file search, computer use, and more. |
What it does
The model is presented as a Flash model that keeps speed and scale while handling agentic work. Its documented pattern is to support long-horizon execution and multi-step workflows rather than only short one-shot replies.
Model shape
It is documented with a 1M-token input limit, 64k output tokens, and support across Gemini App, Gemini API, Gemini Enterprise, Gemini Enterprise Agent Platform, Google AI Mode, Google AI Studio, Google Antigravity, and Android Studio.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | GoogleHost Gemini 3.5 Flash | ||
|---|---|---|---|
| General Info | |||
| Provider | Anthropic | Anthropic | |
| Release Date | May 19, 2026 | June 9, 2026 | May 28, 2026 |
| Knowledge Cutoff | Jan 2025 | — | — |
| Context & Limits | |||
| Context Window | 1.0M Best Context Window | 1M | 1M |
| Pricing (per 1M tokens) | |||
| Input Pricing | $1.50 Best Input Pricing | $10 | $5 |
| Output Pricing | $9 Best Output Pricing | $50 | $25 |
| Modalities | |||
| Inputs | textimagevideofileaudio | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 50.2 | 59.9 Best Intelligence Index | 55.7 |
| Coding Index | 70.1 | 76.5 Best Coding Index | 74.3 |
| Agentic Index | 37.4 | 52.8 Best Agentic Index | 47.2 |
GPQA Benchmark
Graduate-level reasoning and expert Q&A evaluation.
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
IFBench Instruction
Evaluation of strict instruction following.
Benchmark scores are independent evaluations sourced from Artificial Analysis. Intelligence, Coding, and Agentic indices reflect composite performance ratings (0–100).