Specifications
Context Window
—
Input Price/1M
$0.30
Output Price/1M
$2.50
Parameters
—
Speed
214 tok/s
Latency (TTFT)
8.4s
Benchmarks
Gemini 2.5 Flash Preview (Reasoning) results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 14.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LiveCodeBench | 70.0 | 100.0 | Artificial Analysis official API |
| SciCode | 39.0 | 100.0 | — |
| AA Coding Index | 22.2 | 100.0 | — |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 83.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 62.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MATH-500 | 92.6 | 100.0 | Artificial Analysis official API |
| AA Math Index | 73.3 | 100.0 | Artificial Analysis official API |
| AIME 2025 | 73.0 | 100.0 | Artificial Analysis official API |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 20.1 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU Pro | 84.2 | 100.0 | Artificial Analysis official API |
| GPQA Diamond | 79.0 | 100.0 | Artificial Analysis official API |
| IFBench | 50.0 | 100.0 | — |
| HLE | 12.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 32.0 | 100.0 | — |
Information
- Release date
- May 20, 2025
- Tool Calling
- ❌ Not supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: Gemini 2.5 Flash Preview (Reasoning)
What is Gemini 2.5 Flash Preview (Reasoning)?
Gemini 2.5 Flash Preview (Reasoning) is an AI model developed by Google, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Google's cloud API.
Pricing & Costs in 2026
Gemini 2.5 Flash Preview (Reasoning) is usage-based, priced at $0.3/1M input tokens and $2.5/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Benchmarks & Performance
Gemini 2.5 Flash Preview (Reasoning) was evaluated on 15 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show exceptional performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Gemini 2.5 Flash Preview (Reasoning) specializes in text, offering advanced capabilities for creating and processing text content.
Comparison with Alternatives
In the 2026 AI model ecosystem, Gemini 2.5 Flash Preview (Reasoning) competes directly with similarly capable models. Key competitors include GPT (OpenAI), Claude (Anthropic), and open source models like Llama (Meta) and Qwen (Alibaba). The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Gemini 2.5 Flash Preview (Reasoning)?
Gemini 2.5 Flash Preview (Reasoning) is an AI model developed by Google. It is a text model.
How much does Gemini 2.5 Flash Preview (Reasoning) cost?
Gemini 2.5 Flash Preview (Reasoning) costs $0.3/1M input tokens and $2.5/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does Gemini 2.5 Flash Preview (Reasoning) compare with other models?
In available benchmarks, Gemini 2.5 Flash Preview (Reasoning) scored: Terminal-Bench Hard: 14/100, LiveCodeBench: 70/100, SciCode: 39/100. See the full table above for a detailed comparison.
Is Gemini 2.5 Flash Preview (Reasoning) open source?
No, Gemini 2.5 Flash Preview (Reasoning) is a proprietary model from Google. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is Gemini 2.5 Flash Preview (Reasoning) best for?
Gemini 2.5 Flash Preview (Reasoning) excels at general-purpose language tasks.
Last updated: July 17, 2026 • View methodology →