Gemini 3.8 Flash vs DeepSeek V4 Pro 0813
Gemini 3.8 Flash comes out ahead, 74 to 67 on our weighted score, though DeepSeek V4 Pro 0813 is 34% cheaper per token.Gemini 3.8 Flash comes out ahead, 86 to 73 on our weighted score, though DeepSeek V4 Pro 0813 is 34% cheaper per token.
- Our pick
Google
Gemini 3.8 Flash
74/100- ECI158.8
- Price$0.75 / $3.75
- Context1.05M
DeepSeek
DeepSeek V4 Pro 0813
67/100- ECI156.0
- Price$0.66 / $1.98
- Context1M
- Our pick
Google
Gemini 3.8 Flash
86/100- ECI158.8
- Price$0.75 / $3.75
- Context1.05M
DeepSeek
DeepSeek V4 Pro 0813
73/100- ECI156.0
- Price$0.66 / $1.98
- Context1M
Add a model
Make it a three-way comparison.
Gemini 3.8 Flash is our pick
Gemini 3.8 Flash is the better all-round choice, scoring 74/100 against DeepSeek V4 Pro 0813 (67). It leads on capability and inputs & features. DeepSeek V4 Pro 0813 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 3.8 Flash is the better all-round choice, scoring 86/100 against DeepSeek V4 Pro 0813 (73). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 3.8 FlashCapabilities Index (ECI): Gemini 3.8 Flash 158.8 · DeepSeek V4 Pro 0813 156.0
- Lowest priceDeepSeek V4 Pro 0813DeepSeek V4 Pro 0813 $0.99 · Gemini 3.8 Flash $1.50 per 1M tokens (3:1 blend)
- Longest contextGemini 3.8 FlashGemini 3.8 Flash 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 tokens
- Widest inputsGemini 3.8 FlashGemini 3.8 Flash: Text, Images, PDFs, Audio, Video · DeepSeek V4 Pro 0813: Text
- Self-hostingDeepSeek V4 Pro 0813Publishes downloadable weights (MIT)
| Measure | Weight | Gemini 3.8 Flash | DeepSeek V4 Pro 0813 |
|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 86 | 83 |
| Price | 25% | 40 | 48 |
| Inputs & features | 15% | 100 | 45 |
| Context window | 10% | 65 | 64 |
| Overall | 100% | 74/100 | 67/100 |
| Measure | Weight | Gemini 3.8 Flash | DeepSeek V4 Pro 0813 |
|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 86 | 83 |
| Inputs & features | 20% | 100 | 45 |
| Context window | 13% | 65 | 64 |
| Overall | 100% | 86/100 | 73/100 |
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | ||
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | 158.8 (best) | 156.0 |
| ECI rank | #25 of 159 (best) | #43 of 159 |
| ECI confidence interval | 156.8–161.0 | 154.1–158.1 |
| ECI evaluation date | Sep 2, 2026 | Aug 13, 2026 |
| Documented capabilities | Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows | DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes |
| Model parameters | Not published | Not published |
| Output modalities | Text | Text |
| GPQA DiamondGraduate-level science questions | 95.4%high (best) | 91.7%max |
| FrontierMath Tiers 1–3Research-level mathematics | 68.4%high (best) | 64.6%max |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.9%high (best) | 98.6%max |
| SimpleQA VerifiedShort factual questions | 69.7%high (best) | 52.9%max |
| Publisher-reported benchmarks | ||
| DeepSWE 1.1high thinking | 73.7pass@1Reported result | Not published |
| GDPval-AA 2Publisher-reported result | 1545EloReported result | Not published |
| Finance Agent 2Publisher-reported result | 61.4pass@1Reported result | Not published |
| Harvey Legal Agent BenchmarkPublisher-reported result | 10all-pass rateReported result | Not published |
| Terminal-Bench 2.1Publisher-reported result | 89.4pass@1Reported result | Not published |
| Terminal-Bench 4.0Publisher-reported result | 19.1pass@1Reported result | Not published |
| GDP.PDFPublisher-reported result | 35all-pass rateReported result | Not published |
| CharXiv Reasoningwithout tools | 86.2pass@1Reported result | Not published |
| LVBenchagentic | 87.8pass@1Reported result | Not published |
| LVBenchstatic; 1024 frames; without tools | 87.1pass@1Reported result | Not published |
| HLE-Verified · 1811 verified and revised itemsPublisher-reported result | 54.9accuracyReported result | Not published |
| OSWorld 2.0 · before 2026-08-08 patchbatched tool calls; best of 3 runs; 500 steps | 59partial scoreReported result | Not published |
| BioMysteryBench · human-solvablewith tools | 88.8pass@1Reported result | Not published |
| BioMysteryBench · human-difficultwith tools | 56.5pass@1Reported result | Not published |
| LAB-Bench 2 · 11 subtaskswith tools | 86.2macro-averageReported result | Not published |
| Humanity's Last Examwithout tools | Not published | 42.7scoreReported result |
| Humanity's Last Examwith tools | Not published | 60scoreReported result |
| Terminal-Bench 2.1max effort | Not published | 87.9scoreReported result |
| NL2Repomax effort | Not published | 61.5scoreReported result |
| CyberGymmax effort | Not published | 83.3scoreReported result |
| DeepSWEmax effort | Not published | 62.7scoreReported result |
| Toolathlon-VerifiedPublisher-reported result | Not published | 74.1scoreReported result |
| Agents' Last ExamPublisher-reported result | Not published | 25.7scoreReported result |
| AutomationBench · publicPublisher-reported result | Not published | 31.8scoreReported result |
| DSBench-FullStack · internalPublisher-reported result | Not published | 71.1scoreReported result |
| DSBench-Hard · internalPublisher-reported result | Not published | 67.2scoreReported result |
| Price per million tokens | ||
| Input | $0.75 | $0.66 (best) |
| Output | $3.75 | $1.98 (best) |
| Cached input | $0.075 | $0.022 (best) |
| Blended (3:1) | $1.50 | $0.99 (best) |
| Long-context rate | Same rate | Same rate |
| Price source | Official Google API | Official DeepSeek API |
| Limits | ||
| Context window | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max input | Not published | Not published |
| Max output | 65,536 tokens | 384,000 tokens (best) |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | No |
| PDFs | Yes | No |
| Audio | Yes | No |
| Video | Yes | No |
| Reasoning | Yeslow · medium · high | Yeslow · high · max |
| Tool calling | Yes | Yes |
| Structured output | Yes | Yes |
| File attachments | Yes | No |
| Temperature control | Yes | Yes |
| Reasoning control | effort | effort |
| Availability | ||
| Weights | Proprietary | OpenMIT |
| API model ID | gemini-3.8-flash | deepseek-v4-pro |
| API providers | 42 | 54 (best) |
| Released | Sep 2, 2026 | Aug 13, 2026 |
| Knowledge cutoff | Not published | Not published |
| Publisher documentation | Publisher documentation | Publisher documentation · Model weights |
| Source metadata updated | Sep 2, 2026 | Aug 22, 2026 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Gemini 3.8 Flash$15.00
DeepSeek V4 Pro 0813$10.56
Which should you choose?
Which is better: Gemini 3.8 Flash or DeepSeek V4 Pro 0813?
Gemini 3.8 Flash is the better all-round choice, scoring 74/100 against DeepSeek V4 Pro 0813 (67). It leads on capability and inputs & features. DeepSeek V4 Pro 0813 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.Gemini 3.8 Flash is the better all-round choice, scoring 86/100 against DeepSeek V4 Pro 0813 (73). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Gemini 3.8 Flash or DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 is cheaper at $0.66 input / $1.98 output per million tokens (official DeepSeek API price). Gemini 3.8 Flash costs $0.75 input / $3.75 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.99 per million tokens for DeepSeek V4 Pro 0813 versus $1.50 for Gemini 3.8 Flash (1.5× as much).
Which scores higher on benchmarks?
Gemini 3.8 Flash scores higher on the Capabilities Index (ECI): Gemini 3.8 Flash 158.8 (#25 of 159) and DeepSeek V4 Pro 0813 156.0 (#43 of 159). The confidence ranges of the top two overlap (156.8–161.0 vs 154.1–158.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3.8 Flash 95.4%, DeepSeek V4 Pro 0813 91.7%; FrontierMath Tiers 1–3 — Gemini 3.8 Flash 68.4%, DeepSeek V4 Pro 0813 64.6%; OTIS Mock AIME 2024–2025 — Gemini 3.8 Flash 98.9%, DeepSeek V4 Pro 0813 98.6%; SimpleQA Verified — Gemini 3.8 Flash 69.7%, DeepSeek V4 Pro 0813 52.9%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 3.8 Flash and DeepSeek V4 Pro 0813 yet, so there is no like-for-like coding score. On overall capability, Gemini 3.8 Flash leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3.8 Flash has the largest context window at 1,048,576 tokens, against 1,000,000 for DeepSeek V4 Pro 0813. Maximum output per response: Gemini 3.8 Flash up to 65,536, DeepSeek V4 Pro 0813 up to 384,000 tokens.
Which can read images, PDFs, audio or video?
Gemini 3.8 Flash accepts text, images, PDFs, audio and video; DeepSeek V4 Pro 0813 accepts text. Gemini 3.8 Flash handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro 0813 publishes its weights (MIT) and can be self-hosted; Gemini 3.8 Flash is proprietary.
Which is newer?
Gemini 3.8 Flash is the newest, released Sep 2, 2026. DeepSeek V4 Pro 0813 came out Aug 13, 2026.
How do you decide the winner?
This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.