DeepSeek-V3.1 vs Qwen3.5 9B vs Qwen3 14B
Qwen3.5 9B comes out ahead, 72 to 55 and 54 on our weighted score, and it is the cheaper option too.
DeepSeekDeepSeek-V3.1
55/100- ECI139.9
- Price$0.385 / $1.25
- Context131K
- Our pick
Alibaba (Qwen)Qwen3.5 9B
72/100- ECI139.5
- Price$0.10 / $0.15
- Context262K
- Alibaba (Qwen)
Qwen3 14B
54/100- ECI138.2
- Price$0.35 / $1.40
- Context131K
Qwen3.5 9B is our pick
Qwen3.5 9B is the better all-round choice, scoring 72/100 against DeepSeek-V3.1 (55) and Qwen3 14B (54). It leads on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityDeepSeek-V3.1Capabilities Index (ECI): DeepSeek-V3.1 139.9 · Qwen3.5 9B 139.5 · Qwen3 14B 138.2
- Lowest priceQwen3.5 9BQwen3.5 9B $0.113 · DeepSeek-V3.1 $0.601 · Qwen3 14B $0.613 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 9BQwen3.5 9B 262,144 · DeepSeek-V3.1 131,072 · Qwen3 14B 131,072 tokens
- Widest inputsQwen3.5 9BDeepSeek-V3.1: Text · Qwen3.5 9B: Text, Images, Video · Qwen3 14B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek-V3.1 | Qwen3.5 9B | Qwen3 14B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 65 | 65 | 63 |
| Price | 25% | 60 | 95 | 60 |
| Inputs & features | 15% | 35 | 80 | 35 |
| Context window | 10% | 24 | 37 | 24 |
| Overall | 100% | 55/100 | 72/100 | 54/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-V3.1DeepSeek | Qwen3.5 9BAlibaba (Qwen) | Qwen3 14BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.9 (best) | 139.5 | 138.2 |
| ECI rank | #100 of 148 (best) | #101 of 148 | #107 of 148 |
| GPQA DiamondGraduate-level science questions | — | 79.0% (best) | 63.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 61.7% | 66.4% (best) |
| Price per million tokens | |||
| Input | $0.385 | $0.10 (best) | $0.35 |
| Output | $1.25 | $0.15 (best) | $1.40 |
| Cached input | — | — | — |
| Blended (3:1) | $0.601 | $0.113 (best) | $0.613 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 8 providers | Median of 14 providers | Official Alibaba API |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 131,072 tokens |
| Max output | 8,192 tokens | 65,536 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenMIT License | Open | Open |
| API model ID | — | — | qwen3-14b |
| API providers | 8 | 15 (best) | 1 |
| Released | Aug 21, 2025 | Feb 23, 2026 | Apr 29, 2025 |
| Knowledge cutoff | — | — | Apr 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
- Qwen3.5 9B$1.30
- Qwen3 14B$6.30
Which should you choose?
Which is better: DeepSeek-V3.1, Qwen3.5 9B or Qwen3 14B?
Qwen3.5 9B is the better all-round choice, scoring 72/100 against DeepSeek-V3.1 (55) and Qwen3 14B (54). It leads on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-V3.1, Qwen3.5 9B or Qwen3 14B?
Qwen3.5 9B is cheaper at $0.10 input / $0.15 output per million tokens (median across 14 API providers). DeepSeek-V3.1 costs $0.385 input / $1.25 output per million tokens (median across 8 API providers); Qwen3 14B costs $0.35 input / $1.40 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.113 per million tokens for Qwen3.5 9B versus $0.601 for DeepSeek-V3.1 (5.3× as much) and $0.613 for Qwen3 14B (5.4× as much).
Which scores higher on benchmarks?
DeepSeek-V3.1 scores higher on the Capabilities Index (ECI): DeepSeek-V3.1 139.9 (#100 of 148), Qwen3.5 9B 139.5 (#101 of 148) and Qwen3 14B 138.2 (#107 of 148). The confidence ranges of the top two overlap (136.1–143.3 vs 136.5–141.3), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3.1, Qwen3.5 9B and Qwen3 14B yet, so there is no like-for-like coding score. On overall capability, DeepSeek-V3.1 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?
Qwen3.5 9B has the largest context window at 262,144 tokens, against 131,072 for DeepSeek-V3.1 and 131,072 for Qwen3 14B. Maximum output per response: DeepSeek-V3.1 up to 8,192, Qwen3.5 9B up to 65,536, Qwen3 14B up to 8,192 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3.1 accepts text; Qwen3.5 9B accepts text, images and video; Qwen3 14B accepts text. Qwen3.5 9B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (MIT License), so you can self-host them.
Which is newer?
Qwen3.5 9B is the newest, released Feb 23, 2026. DeepSeek-V3.1 came out Aug 21, 2025; Qwen3 14B came out Apr 29, 2025. Knowledge cutoff: Qwen3 14B Apr 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.
