DeepSeek-V3.1 vs Gemini 3 Flash Preview vs Grok 4.20 (Reasoning)
Gemini 3 Flash Preview comes out ahead, 73 to 68 and 55 on our weighted score, though DeepSeek-V3.1 is 47% cheaper per token.
DeepSeekDeepSeek-V3.1
55/100- ECI139.9
- Price$0.385 / $1.25
- Context131K
- Our pick
GoogleGemini 3 Flash Preview
73/100- ECI151.8
- Price$0.50 / $3.00
- Context1.05M
xAIGrok 4.20 (Reasoning)
68/100- ECI152.0
- Price$1.25 / $2.50
- Context1M
Gemini 3 Flash Preview is our pick
Gemini 3 Flash Preview is the better all-round choice, scoring 73/100 against Grok 4.20 (Reasoning) (68) and DeepSeek-V3.1 (55). It leads on inputs & features. DeepSeek-V3.1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGrok 4.20 (Reasoning)Capabilities Index (ECI): Grok 4.20 (Reasoning) 152.0 · Gemini 3 Flash Preview 151.8 · DeepSeek-V3.1 139.9
- Lowest priceDeepSeek-V3.1DeepSeek-V3.1 $0.601 · Gemini 3 Flash Preview $1.13 · Grok 4.20 (Reasoning) $1.56 per 1M tokens (3:1 blend)
- Longest contextGemini 3 Flash PreviewGemini 3 Flash Preview 1,048,576 · Grok 4.20 (Reasoning) 1,000,000 · DeepSeek-V3.1 131,072 tokens
- Widest inputsGemini 3 Flash PreviewDeepSeek-V3.1: Text · Gemini 3 Flash Preview: Text, Images, PDFs, Audio, Video · Grok 4.20 (Reasoning): Text, Images, PDFs
- Self-hostingDeepSeek-V3.1Publishes downloadable weights (MIT License)
| Measure | Weight | DeepSeek-V3.1 | Gemini 3 Flash Preview | Grok 4.20 (Reasoning) |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 65 | 80 | 81 |
| Price | 25% | 60 | 47 | 41 |
| Inputs & features | 15% | 35 | 100 | 80 |
| Context window | 10% | 24 | 61 | 60 |
| Overall | 100% | 55/100 | 73/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-V3.1DeepSeek | Gemini 3 Flash PreviewGoogle | Grok 4.20 (Reasoning)xAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.9 | 151.8 | 152.0 (best) |
| ECI rank | #100 of 148 | #43 of 148 | #41 of 148 (best) |
| GPQA DiamondGraduate-level science questions | — | 89.4% (best) | 89.3% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 51.2% (best) | 44.9% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 95.6% (best) | 92.2% |
| SWE-bench VerifiedFixing real GitHub issues | — | 75.4% | — |
| SimpleQA VerifiedShort factual questions | — | 66.8% (best) | 30.2% |
| Price per million tokens | |||
| Input | $0.385 (best) | $0.50 | $1.25 |
| Output | $1.25 (best) | $3.00 | $2.50 |
| Cached input | — | $0.05 (best) | $0.20 |
| Blended (3:1) | $0.601 (best) | $1.13 | $1.56 |
| Long-context rate | Same rate | Same rate | Over 200K: $2.50 / $5.00 |
| Price source | Median of 8 providers | Official Google API | Official xAI API |
| Limits | |||
| Context window | 131,072 tokens | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max output | 8,192 tokens | 65,536 tokens (best) | 30,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yesminimal · low · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenMIT License | Proprietary | Proprietary |
| API model ID | — | gemini-3-flash-preview | grok-4.20-0309-reasoning |
| API providers | 8 | 20 (best) | 11 |
| Released | Aug 21, 2025 | Dec 17, 2025 | Mar 9, 2026 |
| Knowledge cutoff | — | Jan 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek-V3.1$6.35
- Gemini 3 Flash Preview$11.00
- Grok 4.20 (Reasoning)$17.50
Which should you choose?
Which is better: DeepSeek-V3.1, Gemini 3 Flash Preview or Grok 4.20 (Reasoning)?
Gemini 3 Flash Preview is the better all-round choice, scoring 73/100 against Grok 4.20 (Reasoning) (68) and DeepSeek-V3.1 (55). It leads on inputs & features. DeepSeek-V3.1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-V3.1, Gemini 3 Flash Preview or Grok 4.20 (Reasoning)?
DeepSeek-V3.1 is cheaper at $0.385 input / $1.25 output per million tokens (median across 8 API providers). Gemini 3 Flash Preview costs $0.50 input / $3.00 output per million tokens (official Google API price); Grok 4.20 (Reasoning) costs $1.25 input / $2.50 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.601 per million tokens for DeepSeek-V3.1 versus $1.13 for Gemini 3 Flash Preview (1.9× as much) and $1.56 for Grok 4.20 (Reasoning) (2.6× as much).
Which scores higher on benchmarks?
Grok 4.20 (Reasoning) scores higher on the Capabilities Index (ECI): Grok 4.20 (Reasoning) 152.0 (#41 of 148), Gemini 3 Flash Preview 151.8 (#43 of 148) and DeepSeek-V3.1 139.9 (#100 of 148). The confidence ranges of the top two overlap (149.3–154.4 vs 150.4–153.7), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3.1 and Grok 4.20 (Reasoning) yet, so there is no like-for-like coding score. On overall capability, Grok 4.20 (Reasoning) leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3 Flash Preview has the largest context window at 1,048,576 tokens, against 1,000,000 for Grok 4.20 (Reasoning) and 131,072 for DeepSeek-V3.1. Maximum output per response: DeepSeek-V3.1 up to 8,192, Gemini 3 Flash Preview up to 65,536, Grok 4.20 (Reasoning) up to 30,000 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3.1 accepts text; Gemini 3 Flash Preview accepts text, images, PDFs, audio and video; Grok 4.20 (Reasoning) accepts text, images and PDFs. Gemini 3 Flash Preview handles the widest range of inputs.
Are any of these open source?
DeepSeek-V3.1 publishes its weights (MIT License) and can be self-hosted; Gemini 3 Flash Preview and Grok 4.20 (Reasoning) is proprietary.
Which is newer?
Grok 4.20 (Reasoning) is the newest, released Mar 9, 2026. Gemini 3 Flash Preview came out Dec 17, 2025; DeepSeek-V3.1 came out Aug 21, 2025. Knowledge cutoff: Gemini 3 Flash Preview Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on 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 Oct 4, 2026.
Related comparisons
- DeepSeek-V3.1 vs Qwen3 14BAlibaba (Qwen) · ECI 138.2
- DeepSeek-V3.1 vs Gemini 2.5 FlashGoogle · ECI 140.8
- DeepSeek-V3.1 vs GPT OSS 120BOpenAI · ECI 140.0
- DeepSeek-V3.1 vs GLM-4.7Z.ai (Zhipu) · ECI 143.5
- Gemini 3 Flash Preview vs Kimi K2.5Moonshot AI · ECI 148.0
- Gemini 3 Flash Preview vs Qwen3.6 PlusAlibaba (Qwen) · ECI 147.6
