Google: Gemini 2.5 Flash
Analysis Summary
Google's Gemini 2.5 Flash, released in June 2025, is a high-capability multimodal model supporting text, image, file, audio, and video input. Its intelligence index of 27.0 and coding index of 22.2 place it firmly in the good-to-very-strong tier, and its math index of 73.3 and AIME score of 0.733 confirm strong quantitative reasoning. LiveCodeBench at 0.695 and agentic index of 22.6 make it a credible choice for coding and automation tasks. Instruction-following (IFBench 0.503) and long-context reasoning (LCR 0.617) are both strong.
For businesses, Gemini 2.5 Flash is a versatile workhorse. The 1M token context window, combined with audio and video input, opens up use cases in media analysis, long-document processing, and multimodal customer workflows. Tool use and function calling are supported, enabling agentic pipeline integration. It handles content generation, coding assistance, and structured extraction reliably.
At $0.30 input and $2.50 output per million tokens, it is competitively priced for its capability breadth. Teams looking for a single model that covers reasoning, coding, multimodal input, and long-context tasks without paying frontier-model prices will find Gemini 2.5 Flash a strong fit.
Assessed June 9, 2026
Editorial notes
Gemini 2.5 Flash from Google delivers strong reasoning, full multimodal support including audio and video, tool use, and a 1M token context at competitive pricing.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Google: Gemini 2.5 Flash compares
Google: Gemini 2.5 Flash ranks #131 of 377 AI models we track for overall intelligence, #134 of 314 for coding, #167 of 289 for agentic tasks. Its 1M-token context window is larger than 97% of the models we list. At $0.30 per million input tokens it is cheaper than 43% of comparable models.
About Google: Gemini 2.5 Flash
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Google: Gemini 2.5 Flash stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.30 | $0.000300 |
| Output | $2.50 | $0.002500 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Google: Gemini 2.5 Flash
How much does Google: Gemini 2.5 Flash cost?
Google: Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens.
What is the context window of Google: Gemini 2.5 Flash?
Google: Gemini 2.5 Flash has a context window of 1,048,576 tokens (1M).
Is Google: Gemini 2.5 Flash good for coding?
On our coding benchmark index, Google: Gemini 2.5 Flash ranks #134 of 314 models, placing it in the broader range of the field for code generation and debugging.
What can Google: Gemini 2.5 Flash do?
Google: Gemini 2.5 Flash supports image/vision input, tool use, and function calling.
Who created Google: Gemini 2.5 Flash?
Google: Gemini 2.5 Flash is developed by Google and was released on June 17, 2025.
