DeepSeek V4.1 Flash vs Gemini 3.8 Flash
DeepSeek V4.1 Flash (DeepSeek) and Gemini 3.8 Flash (Google DeepMind) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.8 Flash leads on overall intelligence (ECI 159 vs 157).
- DeepSeek V4.1 Flash is cheaper on input tokens: $0.02 vs $0.75 per 1M.
- Gemini 3.8 Flash ranks higher for coding (79th vs 74th percentile).
| Attribute | DeepSeek V4.1 Flash | Gemini 3.8 Flash |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 157 | 159 |
| Coding | 74 | 79 |
| Math | 68 | 73 |
| Reasoning & Knowledge | 57 | 88 |
| Agentic & Tools | 39 | 81 |
| Specifications | ||
| Developer | DeepSeek | Google DeepMind |
| Family | DeepSeek | Gemini |
| Released | Sep 9, 2026 | Sep 2, 2026 |
| Parameters | 552B | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | 1M | 1M |
| Price — $/M input | $0.02 | $0.75 |
| Price — $/M output | $0.40 | $3.75 |
| Inputs | text, image | text, image, video, file, audio |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 98% | 99% |
| APEX | 40% | 64% |
| ARC-AGI | 95% | 99% |
| ARC-AGI-2 | 73% | 89% |
| GPQA Diamond | 90% | 95% |
| Humanity's Last Exam | 39% | 45% |
| SciCode | 52% | 57% |
| SimpleBench | 67% | 82% |
| SimpleQA Verified | 43% | 70% |
| WebDev Arena | 1614 | 1568 |
| WeirdML | — | 85% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is DeepSeek V4.1 Flash better than Gemini 3.8 Flash?
On Epoch AI's Capabilities Index, Gemini 3.8 Flash scores higher (159) than DeepSeek V4.1 Flash (157). The right pick depends on your task, so compare their coding, math, and reasoning scores in the table above.
Which is cheaper, DeepSeek V4.1 Flash or Gemini 3.8 Flash?
DeepSeek V4.1 Flash is cheaper on input tokens at $0.02 per million, versus $0.75 (representative OpenRouter pricing).
Which has a larger context window, DeepSeek V4.1 Flash or Gemini 3.8 Flash?
Neither: both support up to 1M tokens.
Which is better for coding, DeepSeek V4.1 Flash or Gemini 3.8 Flash?
Gemini 3.8 Flash ranks higher across coding benchmarks like WebDev Arena and SciCode: 79th vs 74th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.