# Gemini 3.6 Flash: price, benchmarks, context

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/gemini-3-6-flash/
- **Idioma:** en
- **Atualizado:** 2026-11-19

---
**12th–39th of 85**

- technical tie with the top score — GPQA Diamond
- technical tie with the top score — GPQA Diamond (OpenRouter)
- technical tie with the top score — OTIS Mock AIME

Methodology v2 · updated November 21, 2026 · [Technical tie](https://meirinho.com.br/en/ia/modelos/metodologia/#empate-tecnico) · [Minimum of 4 benchmarks](https://meirinho.com.br/en/ia/modelos/metodologia/#minimo-3-benchmarks) · [Methodology](https://meirinho.com.br/en/ia/modelos/metodologia/)

Google

# Gemini 3.6 Flash

Benchmarks, price, context and versions

GPQA Diamond

Epoch AI

FrontierMath (tiers 1 to 3)

Epoch AI

Input US$/1M

Official pricing

Output US$/1M

Official pricing

Context

tokens

## Direct answer

**Direct answer:** Gemini 3.6 Flash is a model from Google. 94.1% on GPQA Diamond, per Epoch AI. US$ 0.75 per 1 million input tokens and US$ 3.75 per 1 million output tokens. Current price, valid through December 31, 2026. From January 1, 2027, it goes to US$ 1.50 per 1 million input tokens and US$ 7.50 per 1 million output tokens. On the free tier, submitted data is used to improve Google's products

## ✓ Good for

- technical reasoning on science topics (14th of 195 on GPQA Diamond, per Epoch AI)
- answering short facts with little invention (15th of 87 on SimpleQA Verified, in a statistical tie with one other model, per Epoch AI)
- technical reasoning as the model appears through the API (13th of 134 on GPQA Diamond (OpenRouter), per OpenRouter Benchmarks)
- very long documents or code (a window of 1 million tokens or more, according to OpenRouter)

## ✕ Not the best for

- the ceiling of reasoning on research-level math (44th of 85 on FrontierMath (tiers 1 to 3), per Epoch AI)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. The price is official pricing, published by the lab itself for its own API. Context uses OpenRouter. Scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

## Benchmarks

| GPQA Diamond[? what it is](https://meirinho.com.br/en/ia/modelos/glossario/gpqa-diamond/) | 94.1%**highest score on this metric 96.8%14º / 195 · [Epoch AI](https://epoch.ai/benchmarks/gpqa-diamond), latest version we checked |
| --- | --- |
| OTIS Mock AIME[?](https://meirinho.com.br/en/ia/modelos/glossario/otis-mock-aime/) | 94.2%**highest score on this metric 100%51º / 182 · [Epoch AI](https://epoch.ai/benchmarks/otis-mock-aime-2024-2025), latest version we checked |
| FrontierMath (tiers 1 to 3)[?](https://meirinho.com.br/en/ia/modelos/glossario/frontiermath/) | 58.9%**highest score on this metric 95.1%44º / 85 · [Epoch AI](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2), latest version we checked |
| SimpleQA Verified[?](https://meirinho.com.br/en/ia/modelos/glossario/simpleqa-verified/) | 66.2%**highest score on this metric 94%16º / 87 · [Epoch AI](https://epoch.ai/benchmarks/simpleqa-verified), latest version we checked |
| GPQA Diamond (OpenRouter)[?](https://meirinho.com.br/en/ia/modelos/glossario/gpqa-diamond-openrouter/) | 93.4%**highest score on this metric 96.5%13º / 134 · [OpenRouter Benchmarks](https://openrouter.ai/benchmarks/gpqa-diamond), latest version we checked |
| τ-bench Verified (airline)[?](https://meirinho.com.br/en/ia/modelos/glossario/tau-bench/) | 76.3%**highest score on this metric 82%39º / 130 · [OpenRouter Benchmarks](https://openrouter.ai/benchmarks/tau2-bench-airline), latest version we checked |

## Input US$/1M · Output US$/1M

Input US$/1M

US$ 0.75

Output US$/1M

US$ 3.75

Cache read US$/1M

US$ 0.075

Batch US$/1M

US$ 0.375 / US$ 1.875

From January 1, 2027: US$ 1.50 per 1M input tokens and US$ 7.50 per 1M output · Cache read US$ 0.15 · Batch US$ 0.75 input and US$ 3.75 output · Official pricing

## Key specs

| Lab | [Google](https://meirinho.com.br/en/ia/modelos/lab/google/) |
| --- | --- |
| Origin | the US |
| Family | Gemini Flash provisional data |
| Weights[?](https://meirinho.com.br/en/ia/modelos/glossario/pesos-abertos/) | closed |
| License | no data |
| Also known as | API name: [gemini-3.6-flash](https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash) |
| Context[?](https://meirinho.com.br/en/ia/modelos/glossario/janela-de-contexto/) | 1,048,576 tokens |
| Parameters | no data |
| Input | audio, file, image, text, video |
| OpenRouter usage[?](https://meirinho.com.br/en/ia/modelos/glossario/uso-no-openrouter/) | 0.03% OpenRouter |
| Downloads (30 days)[?](https://meirinho.com.br/en/ia/modelos/glossario/downloads-hugging-face/) | no data |
| Use cases provisional data | [Text](https://meirinho.com.br/en/ia/modelos/uso/texto/) [Agents](https://meirinho.com.br/en/ia/modelos/uso/agentes/) |
| Dates in sources | no official dateJuly 21, 2026, published, per Epoch AIJuly 21, 2026, listed on OpenRouter |

Collected November 17, 2026

## Version history

- September 2, 2026 [Google: Gemini 3.8 Flash](https://openrouter.ai/google/gemini-3.8-flash) OpenRouter, listed on OpenRouter
- August 13, 2026 [Google: Gemini 3.7 Flash](https://openrouter.ai/google/gemini-3.7-flash) OpenRouter, listed on OpenRouter
- July 21, 2026 [Google: Gemini 3.6 Flash](https://openrouter.ai/google/gemini-3.6-flash) OpenRouter, listed on OpenRouter
- May 19, 2026 [Google: Gemini 3.5 Flash](https://openrouter.ai/google/gemini-3.5-flash) OpenRouter, listed on OpenRouter
- December 17, 2025 [Google: Gemini 3 Flash Preview](https://openrouter.ai/google/gemini-3-flash-preview) OpenRouter, listed on OpenRouter

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

## Sources for this model

- Official model page, [Google](https://aistudio.google.com/docs/models).
- Official pricing, [Google](https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash).
- No official launch announcement.
- Benchmarks: each score carries its own source, in the table above.

## FAQ

Gemini 3.6 Flash is a model from Google, with closed weights, used for text, agents.

US$ 0.75 per 1 million input tokens and US$ 3.75 per 1 million output tokens. Current price, valid through December 31, 2026. From January 1, 2027, it goes to US$ 1.50 per 1 million input tokens and US$ 7.50 per 1 million output tokens. On the free tier, submitted data is used to improve Google's products

1,048,576 tokens, per OpenRouter.

No. It is available through API only.

94.1% on GPQA Diamond, per Epoch AI.

No data: there is no SWE-bench Verified measurement for it in open sources.

It was made by Google, a lab from the US.

provisional data

## Compare with

### Models from Google

- [Gemini 1.5 Flash](https://meirinho.com.br/en/ia/modelos/gemini-1-5-flash/)
- [Gemini 1.5 Flash 8B](https://meirinho.com.br/en/ia/modelos/gemini-1-5-flash-8b/)
- [Gemini 2.0 Flash](https://meirinho.com.br/en/ia/modelos/gemini-2-0-flash/)
- [Gemini 2.5 Flash](https://meirinho.com.br/en/ia/modelos/gemini-2-5-flash/)
- [Gemini 3 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-flash/)
- [Gemini 3 Flash Preview](https://meirinho.com.br/en/ia/modelos/gemini-3-flash-preview/)
- [Gemini 3.5 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-5-flash/)
- [Gemini 3.7 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-7-flash/)
- [Gemini 3.8 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-8-flash/)

[See lab](https://meirinho.com.br/en/ia/modelos/lab/google/)

## How to cite

If you use this data, cite the page and the date you accessed it.

```
Adriano Meirinho. "Gemini 3.6 Flash". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/gemini-3-6-flash/. Accessed November 21, 2026.
```

Third-party data follows the license of each source. The full table is available as [CSV](https://meirinho.com.br/ia/modelos/dados.csv) and [JSON](https://meirinho.com.br/ia/modelos/dados.json).

[#](#)
