# Gemini 3.8 Flash vs DeepSeek V4.1 Flash: benchmarks and price

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/comparar/deepseek-v4-1-flash-vs-gemini-3-8-flash/
- **Idioma:** en
- **Atualizado:** 2026-11-17

---
AI models

# Gemini 3.8 Flash vs DeepSeek V4.1 Flash

Same criteria, side by side. Where the gap is small, it may be measurement noise.

Gemini 3.8 Flash

Input US$/1M / Output US$/1M · Official pricing

DeepSeek V4.1 Flash

Input US$/1M / Output US$/1M · Official pricing

GPQA Diamond

95.4% · 89.8%

Gemini 3.8 Flash · DeepSeek V4.1 Flash

## Direct answer

Pick Gemini 3.8 Flash if scores come first: it leads on GPQA Diamond, FrontierMath and SimpleQA Verified. Pick DeepSeek V4.1 Flash if τ-bench Verified matter more, where it leads, or if cost does: at official prices it charges US$ 0.30 versus US$ 0.75 per 1M input tokens and US$ 1.20 versus US$ 3.75 per 1M output.

Gemini 3.8 Flash

- GPQA Diamond **+5.6 p.p.**
- FrontierMath **+1 p.p.**
- SimpleQA Verified **+26.8 p.p.**

statistical tie

| Metric | Gemini 3.8 Flash | DeepSeek V4.1 Flash | Source |
| --- | --- | --- | --- |
| Input US$/1M | US$ 0.75 / US$ 3.75 Official pricing Current price, valid through December 31, 2026 On the free tier, submitted data is used to improve Google's products Cache read US$ 0.15 Batch US$ 0.75 input and US$ 3.75 output | US$ 0.30 / US$ 1.20 Official pricing peak hours |  |
| Output US$/1M | US$ 3.75 | US$ 1.20 |  |
| Context | 1,048,576 | 1,048,576 |  |
| BENCHMARKS |
| GPQA Diamond | **95.4%****between 3rd and 12th of 250 | 89.8%**between 46th and 71st of 250 | [Epoch AI](https://epoch.ai/benchmarks/gpqa-diamond) |
| OTIS Mock AIME saturated | 98.9%** statistical tie with the top score | 98.3%** statistical tie with the top score | [Epoch AI](https://epoch.ai/benchmarks/otis-mock-aime-2024-2025) |
| FrontierMath (tiers 1 to 3) | **68.4%****between 32nd and 35th of 85 | 67.4%**between 33rd and 35th of 85 | [Epoch AI](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| SimpleQA Verified | **69.7%****between 10th and 13th of 87 | 42.9%**between 46th and 48th of 87 | [Epoch AI](https://epoch.ai/benchmarks/simpleqa-verified) |
| τ-bench Verified (airline) | 76.7%**between 22nd and 46th of 130 | **77.8%****between 10th and 30th of 130 | [OpenRouter Benchmarks](https://openrouter.ai/benchmarks/tau2-bench-airline) |
| OTIS Mock AIME saturated | 98.9%** statistical tie with the top score | 98.3%** statistical tie with the top score | [Epoch AI](https://epoch.ai/benchmarks/otis-mock-aime-2024-2025) |

Official pricing: Google, November 18, 2026

Prices in US$ per 1 million tokens, input / output. “From” marks the price the lab has already published on its official pricing page for a future date.

## Compare with

### Compare with

- [Gemini 3.8 Flash vs Claude Sonnet 5.5](https://meirinho.com.br/en/ia/modelos/comparar/claude-sonnet-5-5-vs-gemini-3-8-flash/)

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

## Sources

- [Epoch AI](https://epoch.ai/benchmarks), CC BY 4.0, latest version we checked.
- [OpenRouter Benchmarks](https://openrouter.ai/benchmarks), CC BY 4.0, latest version we checked.
- [OpenRouter](https://openrouter.ai/api/v1/models), dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.

## How to cite

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

```
Adriano Meirinho. "Gemini 3.8 Flash vs DeepSeek V4.1 Flash". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/comparar/deepseek-v4-1-flash-vs-gemini-3-8-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).

[#](#)
