DeepSeek-V3.1 vs Qwen3 235B-A22B vs Qwen3 14B
Too close to call on our weighted score (DeepSeek-V3.1 55, Qwen3 14B 54, Qwen3 235B-A22B 51). The right pick depends on what you value most.
DeepSeekDeepSeek-V3.1
55/100- ECI139.9
- Price$0.385 / $1.25
- Context131K
Alibaba (Qwen)Qwen3 235B-A22B
51/100- ECI139.4
- Price$0.70 / $2.80
- Context131K
- Alibaba (Qwen)
Qwen3 14B
54/100- ECI138.2
- Price$0.35 / $1.40
- Context131K
Too close to call
It is close. Our weighted score puts them within 1 points (DeepSeek-V3.1 55/100, Qwen3 14B 54/100, Qwen3 235B-A22B 51/100), so choose by what matters most for your work: DeepSeek-V3.1 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityDeepSeek-V3.1Capabilities Index (ECI): DeepSeek-V3.1 139.9 · Qwen3 235B-A22B 139.4 · Qwen3 14B 138.2
- Lowest priceDeepSeek-V3.1DeepSeek-V3.1 $0.601 · Qwen3 14B $0.613 · Qwen3 235B-A22B $1.23 per 1M tokens (3:1 blend)
- Longest contextAbout the sameDeepSeek-V3.1 131,072 · Qwen3 235B-A22B 131,072 · Qwen3 14B 131,072 tokens
- Widest inputsSame inputsDeepSeek-V3.1: Text · Qwen3 235B-A22B: Text · Qwen3 14B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek-V3.1 | Qwen3 235B-A22B | Qwen3 14B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 65 | 65 | 63 |
| Price | 25% | 60 | 46 | 60 |
| Inputs & features | 15% | 35 | 35 | 35 |
| Context window | 10% | 24 | 24 | 24 |
| Overall | 100% | 55/100 | 51/100 | 54/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-V3.1DeepSeek | Qwen3 235B-A22BAlibaba (Qwen) | Qwen3 14BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.9 (best) | 139.4 | 138.2 |
| ECI rank | #100 of 148 (best) | #103 of 148 | #107 of 148 |
| GPQA DiamondGraduate-level science questions | — | 70.7% (best) | 63.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 66.4% |
| Price per million tokens | |||
| Input | $0.385 | $0.70 | $0.35 (best) |
| Output | $1.25 (best) | $2.80 | $1.40 |
| Cached input | — | — | — |
| Blended (3:1) | $0.601 (best) | $1.23 | $0.613 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 8 providers | Official Alibaba API | Official Alibaba API |
| Limits | |||
| Context window | 131,072 tokens | 131,072 tokens | 131,072 tokens |
| Max output | 8,192 tokens | 16,384 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenMIT License | Open | Open |
| API model ID | — | qwen3-235b-a22b | qwen3-14b |
| API providers | 8 (best) | 7 | 1 |
| Released | Aug 21, 2025 | Apr 28, 2025 | Apr 29, 2025 |
| Knowledge cutoff | — | Apr 2025 | 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 235B-A22B$12.60
- Qwen3 14B$6.30
Which should you choose?
Which is better: DeepSeek-V3.1, Qwen3 235B-A22B or Qwen3 14B?
It is close. Our weighted score puts them within 1 points (DeepSeek-V3.1 55/100, Qwen3 14B 54/100, Qwen3 235B-A22B 51/100), so choose by what matters most for your work: DeepSeek-V3.1 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-V3.1, Qwen3 235B-A22B or Qwen3 14B?
DeepSeek-V3.1 is cheaper at $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); Qwen3 235B-A22B costs $0.70 input / $2.80 output per million tokens (official Alibaba 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 $0.613 for Qwen3 14B (1× as much) and $1.23 for Qwen3 235B-A22B (2× 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 235B-A22B 139.4 (#103 of 148) and Qwen3 14B 138.2 (#107 of 148). The confidence ranges of the top two overlap (136.1–143.3 vs 135.2–140.8), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3.1, Qwen3 235B-A22B 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?
DeepSeek-V3.1, Qwen3 235B-A22B and Qwen3 14B share the same 131,072-token context window. Maximum output per response: DeepSeek-V3.1 up to 8,192, Qwen3 235B-A22B up to 16,384, Qwen3 14B up to 8,192 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3.1 accepts text; Qwen3 235B-A22B accepts text; Qwen3 14B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (MIT License), so you can self-host them.
Which is newer?
DeepSeek-V3.1 is the newest, released Aug 21, 2025. Qwen3 14B came out Apr 29, 2025; Qwen3 235B-A22B came out Apr 28, 2025. Knowledge cutoff: Qwen3 235B-A22B Apr 2025, 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.
