DeepSeek-V3 vs Llama 4 Maverick 17B Instruct vs Qwen3 30B A3B
Too close to call on our weighted score (Llama 4 Maverick 17B Instruct 57, Qwen3 30B A3B 57, DeepSeek-V3 49). The right pick depends on what you value most.
DeepSeekDeepSeek-V3
49/100- ECI132.3
- Price$0.32 / $1.10
- Context131K
MetaLlama 4 Maverick 17B Instruct
57/100- ECI132.3
- Price$0.245 / $0.838
- Context1M
Alibaba (Qwen)Qwen3 30B A3B
57/100- ECI136.2
- Price$0.108 / $0.475
- Context131K
Too close to call
It is close. Our weighted score puts them within a point (Llama 4 Maverick 17B Instruct 57/100, Qwen3 30B A3B 57/100, DeepSeek-V3 49/100), so choose by what matters most for your work: Qwen3 30B A3B for raw capability and Llama 4 Maverick 17B Instruct for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityQwen3 30B A3BCapabilities Index (ECI): Qwen3 30B A3B 136.2 · Llama 4 Maverick 17B Instruct 132.3 · DeepSeek-V3 132.3
- Lowest priceQwen3 30B A3BQwen3 30B A3B $0.20 · Llama 4 Maverick 17B Instruct $0.393 · DeepSeek-V3 $0.515 per 1M tokens (3:1 blend)
- Longest contextLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct 1,000,000 · DeepSeek-V3 131,072 · Qwen3 30B A3B 131,072 tokens
- Widest inputsLlama 4 Maverick 17B InstructDeepSeek-V3: Text · Llama 4 Maverick 17B Instruct: Text, Images · Qwen3 30B A3B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek-V3 | Llama 4 Maverick 17B Instruct | Qwen3 30B A3B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 55 | 55 | 59 |
| Price | 25% | 61 | 66 | 80 |
| Inputs & features | 15% | 25 | 50 | 35 |
| Context window | 10% | 25 | 60 | 25 |
| Overall | 100% | 49/100 | 57/100 | 57/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-V3DeepSeek | Llama 4 Maverick 17B InstructMeta | Qwen3 30B A3BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 132.3 | 132.3 | 136.2 (best) |
| ECI rank | #136 of 165 | #135 of 165 | #126 of 165 (best) |
| GPQA DiamondGraduate-level science questions | 56.5% | 67.0% (best) | 61.7% |
| OTIS Mock AIME 2024–2025Competition mathematics | 15.8% | 20.6% | 62.8% (best) |
| Price per million tokens | |||
| Input | $0.32 | $0.245 | $0.108 (best) |
| Output | $1.10 | $0.838 | $0.475 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.515 | $0.393 | $0.20 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 8 providers | Median of 16 providers | Median of 14 providers |
| Limits | |||
| Context window | 131,072 tokens | 1,000,000 tokens (best) | 131,072 tokens |
| Max output | 8,192 tokens | 16,384 tokens (best) | 16,384 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenDeepSeek Model License | Open | Open |
| API model ID | — | — | — |
| API providers | 8 | 16 (best) | 14 |
| Released | Dec 26, 2024 | Apr 5, 2025 | Apr 28, 2025 |
| Knowledge cutoff | — | 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
- Llama 4 Maverick 17B Instruct$4.13
- Qwen3 30B A3B$2.03
Which should you choose?
Which is better: DeepSeek-V3, Llama 4 Maverick 17B Instruct or Qwen3 30B A3B?
It is close. Our weighted score puts them within a point (Llama 4 Maverick 17B Instruct 57/100, Qwen3 30B A3B 57/100, DeepSeek-V3 49/100), so choose by what matters most for your work: Qwen3 30B A3B for raw capability and Llama 4 Maverick 17B Instruct for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-V3, Llama 4 Maverick 17B Instruct or Qwen3 30B A3B?
Qwen3 30B A3B is cheaper at $0.108 input / $0.475 output per million tokens (median across 14 API providers). Llama 4 Maverick 17B Instruct costs $0.245 input / $0.838 output per million tokens (median across 16 API providers); DeepSeek-V3 costs $0.32 input / $1.10 output per million tokens (median across 8 API providers). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for Qwen3 30B A3B versus $0.393 for Llama 4 Maverick 17B Instruct (2× as much) and $0.515 for DeepSeek-V3 (2.6× as much).
Which scores higher on benchmarks?
Qwen3 30B A3B scores higher on the Capabilities Index (ECI): Qwen3 30B A3B 136.2 (#126 of 165), Llama 4 Maverick 17B Instruct 132.3 (#135 of 165) and DeepSeek-V3 132.3 (#136 of 165). The confidence ranges of the top two overlap (130.8–138.5 vs 128.6–134.2), so treat the gap as small. On individual benchmarks: GPQA Diamond — Llama 4 Maverick 17B Instruct 67.0%, Qwen3 30B A3B 61.7%, DeepSeek-V3 56.5%; OTIS Mock AIME 2024–2025 — Qwen3 30B A3B 62.8%, Llama 4 Maverick 17B Instruct 20.6%, DeepSeek-V3 15.8%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3, Llama 4 Maverick 17B Instruct and Qwen3 30B A3B yet, so there is no like-for-like coding score. On overall capability, Qwen3 30B A3B 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?
Llama 4 Maverick 17B Instruct has the largest context window at 1,000,000 tokens, against 131,072 for DeepSeek-V3 and 131,072 for Qwen3 30B A3B. Maximum output per response: DeepSeek-V3 up to 8,192, Llama 4 Maverick 17B Instruct up to 16,384, Qwen3 30B A3B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3 accepts text; Llama 4 Maverick 17B Instruct accepts text and images; Qwen3 30B A3B accepts text. Llama 4 Maverick 17B Instruct handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (DeepSeek Model License), so you can self-host them.
Which is newer?
Qwen3 30B A3B is the newest, released Apr 28, 2025. Llama 4 Maverick 17B Instruct came out Apr 5, 2025; DeepSeek-V3 came out Dec 26, 2024. Knowledge cutoff: 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 Nov 2, 2026.
Related comparisons
- DeepSeek-V3 vs Magistral SmallMistral AI · ECI 133.1
- DeepSeek-V3 vs GPT-4.1 miniOpenAI · ECI 134.9
- DeepSeek-V3 vs QwQ 32BAlibaba (Qwen) · ECI 137.5
- Llama 4 Maverick 17B Instruct vs Magistral SmallMistral AI · ECI 133.1
- Llama 4 Maverick 17B Instruct vs GPT-4.1 miniOpenAI · ECI 134.9
- Llama 4 Maverick 17B Instruct vs Gemini 2.5 Flash-Lite Preview 06-17Google · ECI 133.8
