Gemini 2.5 Flash (Reasoning)
Intelligence
27
#190/523
Coding
22.2
#192/429
Math
73.3
#85/265
Speed
233 tok/s
TTFT: 11.30s
Pricing
$0.30 / $2.50
per 1M tokens (in/out)
A thinking model designed for a balance between price and performance. It builds upon Gemini 2.0 Flash with upgraded reasoning, hybrid thinking control, multimodal capabilities (text, image, video, audio input), and a 1M token input context window.
Gemini 2.5 Flash (Reasoning) is Google’s advanced model designed for reasoning tasks. It processes at 232.52 tokens per second and is priced at $0.3 per million input tokens, targeting professional users.
When to Use Gemini 2.5 Flash (Reasoning)
✓ Best For
- Complex reasoning tasks
- Mathematical problem solving
- Coding assistance
✗ Not Ideal For
- High-speed applications requiring low latency
- Basic conversational tasks
How Gemini 2.5 Flash (Reasoning) Compares
Intelligence Index · Higher is better
AlibabaDeepSeekGoogleOpenAI
Benchmark Profile
Coding Index
MistralGoogleKimi
Output Speed · tok/s
AlibabaNVIDIAGoogleStepFun
Math Index
Allen Institute for AIAnthropicGoogleAlibabaZ AI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (15)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 27 | |
| Coding Index | 22.2 | |
| Math Index | 73.3 | |
| MMLU-Pro | 832% | |
| GPQA | 79% | |
| LiveCodeBench | 695% | |
| HLE | 111% | |
| SciCode | 39.4% | |
| IFBench | 50.3% | |
| LCR | 61.7% | |
| TerminalBench Hard | 13.6% | |
| Tau2 | 31.6% | |
| AIME | 82.3% | |
| AIME 2025 | 73.3% | |
| MATH 500 | 98.1% |
Data: Artificial Analysis · Updated: April 1, 2026
Frequently Asked Questions (15)
When was Gemini 2.5 Flash (Reasoning) released?
Gemini 2.5 Flash (Reasoning) was released on May 20, 2025.
Who created Gemini 2.5 Flash (Reasoning)?
Gemini 2.5 Flash (Reasoning) was created by Google.
How intelligent is Gemini 2.5 Flash (Reasoning)?
Gemini 2.5 Flash (Reasoning) scores 27 on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 20).
How fast is Gemini 2.5 Flash (Reasoning)?
Gemini 2.5 Flash (Reasoning) generates output at 229.5 tokens per second (based on Google's API), which is well above average compared to other reasoning models in a similar price tier (median: 94.3 t/s).
What is the latency of Gemini 2.5 Flash (Reasoning)?
Gemini 2.5 Flash (Reasoning) has a time to first token (TTFT) of 15.24s (based on Google's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 1.79s).
How much does Gemini 2.5 Flash (Reasoning) cost?
Gemini 2.5 Flash (Reasoning) costs $0.30 per 1M input tokens (somewhat higher than average, median: $0.25) and $2.50 per 1M output tokens (at the higher end, median: $0.90), based on Google's API.
What is Gemini 2.5 Flash (Reasoning) API pricing?
Gemini 2.5 Flash (Reasoning) costs $0.30 per 1M input tokens and $2.50 per 1M output tokens (based on Google's API). For a blended rate (3:1 input to output ratio), this is $0.85 per 1M tokens. Pricing may vary by provider.
How verbose is Gemini 2.5 Flash (Reasoning)?
When evaluated on the Intelligence Index, Gemini 2.5 Flash (Reasoning) generated 52M output tokens, which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 20M).
Is Gemini 2.5 Flash (Reasoning) a reasoning model?
Yes, Gemini 2.5 Flash (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Gemini 2.5 Flash (Reasoning) support?
Gemini 2.5 Flash (Reasoning) supports text, image, speech, and video input.
What output modalities does Gemini 2.5 Flash (Reasoning) support?
Gemini 2.5 Flash (Reasoning) supports text output.
Can Gemini 2.5 Flash (Reasoning) process images?
Yes, Gemini 2.5 Flash (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Gemini 2.5 Flash (Reasoning) multimodal?
Yes, Gemini 2.5 Flash (Reasoning) is multimodal. It can process text, image, speech, and video input and generate text output.
What is the context window of Gemini 2.5 Flash (Reasoning)?
Gemini 2.5 Flash (Reasoning) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is Gemini 2.5 Flash (Reasoning) open source?
No, Gemini 2.5 Flash (Reasoning) is proprietary. The model weights are not publicly available.
