Gemini 2.5 Flash by Google demonstrates strong general intelligence, fast output speed, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Massive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardHuman preference ELO from blind head-to-head votes
LMSYS / HuggingFaceCoding Benchmarks
Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Multi-turn service agent making tool calls under strict policy constraints
OpenRouter (measured)Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 33 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Kenari | $0 | $0 | — | 1.0M | — |
| QiHang | $0.09 | $0.71 | — | 1.0M | — |
| Poe | $0.21 | $1.8 | $0.021 | 1.1M | — |
| Jiekou.AI | $0.27 | $2.25 | — | 1.0M | — |
| Cortecs | $0.299 | $2.491 | $0.029 | 1.0M | — |
| 302.AI | $0.3 | $2.5 | — | 1.0M | — |
| Abacus | $0.3 | $2.5 | $0.03 | 1.0M | — |
| AIHubMix | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Auriko | $0.3 | $2.5 | $0.03 | 1.0M | — |
| CrossModel | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Databricks | $0.3 | $2.5 | $0.03 | 1.0M | — |
| DevPass (LLM Gateway) | $0.3 | $2.5 | $0.03 | 1.0M | — |
| FastRouter | $0.3 | $2.5 | $0.0375 | 1.0M | — |
| FrogBot | $0.3 | $2.5 | $0.075 | 1.0M | — |
| $0.3 | $2.5 | $0.03 | 1.0M | Supported | |
| Impossibl | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Kilo Gateway | $0.3 | $2.5 | $0.03 | 1.0M | — |
| LLM Gateway | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Merge Gateway | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Modelis | $0.3 | $2.5 | — | 1.0M | — |
| NanoGPT | $0.3 | $2.5 | $0.03 | 1.0M | — |
| NEAR AI Cloud | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Ofox | $0.3 | $2.5 | $0.03 | 1.0M | — |
| OpenRouter | $0.3 | $2.5 | $0.03 | 1.0M | Supported |
| OrcaRouter | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Perplexity Agent | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Requesty | $0.3 | $2.5 | $0.075 | 1.0M | — |
| SAP AI Core | $0.3 | $2.5 | $0.03 | 1.0M | — |
| Vercel AI Gateway | $0.3 | $2.5 | $0.03 | 1.0M | Supported |
| Vertex | $0.3 | $2.5 | $0.03 | 1.0M | Supported |
| ZenMux | $0.3 | $2.5 | $0.07 | 1.0M | — |
| AnyAPI | — | — | — | 1.0M | — |
| Qiniu | — | — | — | 1.0M | — |
Gemini 2.5 Flash — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare Gemini 2.5 Flash With
Gemini 2.5 Flash — Frequently Asked Questions
How intelligent is Gemini 2.5 Flash?
Gemini 2.5 Flash scores 1320 on the Chatbot Arena ELO rating, making it a mid-tier AI model. This score is based on blind head-to-head human preference voting.
How much does Gemini 2.5 Flash cost?
Gemini 2.5 Flash costs $0.30 per 1M input tokens and $2.5 per 1M output tokens. This makes it one of the more affordable models.
How fast is Gemini 2.5 Flash?
Gemini 2.5 Flash generates output at 251 tokens per second, which is very fast compared to other models. The time to first token is 410 ms.
How good is Gemini 2.5 Flash at coding?
Gemini 2.5 Flash achieves 38.0% on SWE-bench Verified, demonstrating moderate real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is Gemini 2.5 Flash at math and reasoning?
Gemini 2.5 Flash scores 76.0% on the MATH benchmark (competition-level mathematics). It also achieves 72.7% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of Gemini 2.5 Flash?
Gemini 2.5 Flash has a context window of 1.0M tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Gemini 2.5 Flash?
Gemini 2.5 Flash was created by Google. It is classified as a mid model in our catalogue.
Is Gemini 2.5 Flash open source?
No, Gemini 2.5 Flash is a proprietary model. It is available through Google's API and compatible providers.