DeepSeek-V3 vs Gemini 2.0 Flash vs Llama 4 Maverick 17B Instruct
Gemini 2.0 Flash comes out ahead, 65 to 55 and 45 on our weighted score.
DeepSeekDeepSeek-V3
45/100- ECI132.3
- Price$0.32 / $1.10
- Context131K
- Our pick
GoogleGemini 2.0 Flash
65/100- ECI134.7
- Price—
- Context1.05M
MetaLlama 4 Maverick 17B Instruct
55/100- ECI132.2
- Price$0.321 / $0.91
- Context1M
Gemini 2.0 Flash is our pick
Gemini 2.0 Flash is the better all-round choice, scoring 65/100 against Llama 4 Maverick 17B Instruct (55) and DeepSeek-V3 (45). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGemini 2.0 FlashCapabilities Index (ECI): Gemini 2.0 Flash 134.7 · DeepSeek-V3 132.3 · Llama 4 Maverick 17B Instruct 132.2
- Lowest priceLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct $0.468 · DeepSeek-V3 $0.515 per 1M tokens (3:1 blend) · Gemini 2.0 Flash unpriced
- Longest contextGemini 2.0 FlashGemini 2.0 Flash 1,048,576 · Llama 4 Maverick 17B Instruct 1,000,000 · DeepSeek-V3 131,072 tokens
- Widest inputsGemini 2.0 FlashDeepSeek-V3: Text · Gemini 2.0 Flash: Text, Images, PDFs, Audio, Video · Llama 4 Maverick 17B Instruct: Text, Images
- Self-hostingDeepSeek-V3 and Llama 4 Maverick 17B InstructPublishes downloadable weights (DeepSeek Model License)
| Measure | Weight | DeepSeek-V3 | Gemini 2.0 Flash | Llama 4 Maverick 17B Instruct |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 56 | 59 | 56 |
| Inputs & features | 20% | 25 | 90 | 50 |
| Context window | 13% | 24 | 61 | 60 |
| Overall | 100% | 45/100 | 65/100 | 55/100 |
Left out because at least one model lacks the data: price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-V3DeepSeek | Gemini 2.0 FlashGoogle | Llama 4 Maverick 17B InstructMeta |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 132.3 | 134.7 (best) | 132.2 |
| ECI rank | #121 of 148 | #116 of 148 (best) | #122 of 148 |
| GPQA DiamondGraduate-level science questions | 56.5% | — | 67.0% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 15.8% | — | 20.6% (best) |
| Price per million tokens | |||
| Input | $0.32 (best) | — | $0.321 |
| Output | $1.10 | — | $0.91 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.515 | — | $0.468 (best) |
| Long-context rate | Same rate | — | Same rate |
| Price source | Median of 5 providers | — | Median of 6 providers |
| Limits | |||
| Context window | 131,072 tokens | 1,048,576 tokens (best) | 1,000,000 tokens |
| Max output | 8,192 tokens | 8,192 tokens | 16,384 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenDeepSeek Model License | Proprietary | Open |
| API model ID | — | — | — |
| API providers | 5 | — | 6 (best) |
| Released | Dec 26, 2024 | Dec 11, 2024 | Apr 5, 2025 |
| Knowledge cutoff | — | Jun 2024 | Aug 2024 |
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$5.40
- Gemini 2.0 Flash—
- Llama 4 Maverick 17B Instruct$5.03
Which should you choose?
Which is better: DeepSeek-V3, Gemini 2.0 Flash or Llama 4 Maverick 17B Instruct?
Gemini 2.0 Flash is the better all-round choice, scoring 65/100 against Llama 4 Maverick 17B Instruct (55) and DeepSeek-V3 (45). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, DeepSeek-V3, Gemini 2.0 Flash or Llama 4 Maverick 17B Instruct?
Llama 4 Maverick 17B Instruct is cheaper at $0.321 input / $0.91 output per million tokens (median across 6 API providers). DeepSeek-V3 costs $0.32 input / $1.10 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.468 per million tokens for Llama 4 Maverick 17B Instruct versus $0.515 for DeepSeek-V3 (1.1× as much). Gemini 2.0 Flash has no published per-token price.
Which scores higher on benchmarks?
Gemini 2.0 Flash scores higher on the Capabilities Index (ECI): Gemini 2.0 Flash 134.7 (#116 of 148), DeepSeek-V3 132.3 (#121 of 148) and Llama 4 Maverick 17B Instruct 132.2 (#122 of 148). The confidence ranges of the top two overlap (124.3–136.7 vs 127.5–135.5), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3, Gemini 2.0 Flash and Llama 4 Maverick 17B Instruct yet, so there is no like-for-like coding score. On overall capability, Gemini 2.0 Flash 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 2.0 Flash has the largest context window at 1,048,576 tokens, against 1,000,000 for Llama 4 Maverick 17B Instruct and 131,072 for DeepSeek-V3. Maximum output per response: DeepSeek-V3 up to 8,192, Gemini 2.0 Flash up to 8,192, Llama 4 Maverick 17B Instruct up to 16,384 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3 accepts text; Gemini 2.0 Flash accepts text, images, PDFs, audio and video; Llama 4 Maverick 17B Instruct accepts text and images. Gemini 2.0 Flash handles the widest range of inputs.
Are any of these open source?
DeepSeek-V3 and Llama 4 Maverick 17B Instruct publishes its weights (DeepSeek Model License) and can be self-hosted; Gemini 2.0 Flash is proprietary.
Which is newer?
Llama 4 Maverick 17B Instruct is the newest, released Apr 5, 2025. DeepSeek-V3 came out Dec 26, 2024; Gemini 2.0 Flash came out Dec 11, 2024. Knowledge cutoff: Gemini 2.0 Flash Jun 2024, Llama 4 Maverick 17B Instruct Aug 2024.
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 vs Magistral SmallMistral AI · ECI 133.2
- DeepSeek-V3 vs GPT-4.1 miniOpenAI · ECI 135.0
- DeepSeek-V3 vs QwQ 32BAlibaba (Qwen) · ECI 137.6
- Gemini 2.0 Flash vs Claude Sonnet 3.5 v2Anthropic · ECI 133.5
- Gemini 2.0 Flash vs GPT-4.1 miniOpenAI · ECI 135.0
- Gemini 2.0 Flash vs Mistral Medium 3Mistral AI · ECI 134.1
