In short
How they differ.
Worked out from the figures below. Prices and specs are the makers' own, read Oct 20, 2026.
- DeepSeek-V4.1-Flash-1017 is cheaper per output token: $1.20 against $3.75 per million tokens, so Gemini 3.8 Flash costs 3.1 times as much.
- Gemini 3.8 Flash reads more at once: a context window of 1M tokens against 1M.
- DeepSeek-V4.1-Flash-1017 can be downloaded and run on your own machine; Gemini 3.8 Flash can't.
- On the 1 independent board that rank both, DeepSeek-V4.1-Flash-1017 places higher on 1 and Gemini 3.8 Flash on 0.
Side by side
The specs.
| DeepSeek-V4.1-Flash-1017 | Gemini 3.8 Flash | |
|---|---|---|
| Made by | DeepSeek · China | Google · US |
| Released | Oct 17, 2026 | Sep 2, 2026 |
| Price per 1M tokens | $0.30 in / $1.20 out (peak-hours price) | $0.75 in / $3.75 out (introductory price) |
| Context window | 1M | 1M |
| Takes in | text, image | text, image, video, audio, pdf |
| Download and run it yourself | Yes (MIT) | No |
| Size | 552B backbone parameters parameters, 8B per token during prefill, 16B during decode active | Not published |
| Maker says | “Stronger benchmark performance, faster task completion, and shorter outputs than the previous version.” | “Gemini 3.8 Flash is our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows—all with the speed and cost efficiency of Flash.” |
| Sources | Prices, Oct 20, 2026 · Description | Prices, Oct 20, 2026 · Description |
Independent tests
Where they place.
Position on each board we follow (1 is best). Epoch AI's and Vectara's scores are shown; the other boards are linked for their own figures.
| Board | DeepSeek-V4.1-Flash-1017 | Gemini 3.8 Flash |
|---|---|---|
| Epoch Capabilities IndexEpoch AI, Oct 20, 2026 | Not listed | #19157.2 |
| LMArena textLMArena, Oct 15, 2026 | Not listed | #9 |
| LMArena creative writingLMArena, Oct 15, 2026 | Not listed | #7 |
| LMArena mathLMArena, Oct 15, 2026 | Not listed | #4 |
| LMArena visionLMArena, Oct 19, 2026 | Not listed | #12 |
| LMArena Agent ArenaLMArena, Oct 19, 2026 | Not listed | #15 |
| Humanity's Last ExamScale AI | Not listed | #8 |
| SWE-Bench ProScale AI, Sep 22, 2026 | Not listed | #12 |
| Remote Labor IndexScale AI | Not listed | #7 |
| Vals IndexVals AI, Oct 19, 2026 | #8 | #13 |
| Terminal-Bench 4.0Vals AI, Oct 19, 2026 | #17 | Not listed |
| Vibe Code BenchVals AI, Oct 18, 2026 | #11 | Not listed |
| GPQA Diamond (run by Vals AI, archived)Vals AI, Sep 1, 2026 | Not listed | #4 |
| MMMU Pro (run by Vals AI, archived)Vals AI, Sep 1, 2026 | Not listed | #4 |
| CUA-bench (games)Vals AI, Oct 13, 2026 | Not listed | #9 |
More comparisons