Qwen3.5 9B Base vs Qwen3.5 35B-A3B Base vs Mercury 2
Too close to call on our weighted score (Mercury 2 52, Qwen3.5 9B Base 50, Qwen3.5 35B-A3B Base 45). The right pick depends on what you value most.
Alibaba (Qwen)Qwen3.5 9B Base
50/100- ECI—
- Price$0.30 / $0.807
- Context262K
- Alibaba (Qwen)
Qwen3.5 35B-A3B Base
45/100- ECI—
- Price$0.54 / $1.33
- Context262K
InceptionMercury 2
52/100- ECI—
- Price$0.25 / $0.75
- Context128K
Too close to call
It is close. Our weighted score puts them within 2 points (Mercury 2 52/100, Qwen3.5 9B Base 50/100, Qwen3.5 35B-A3B Base 45/100), so choose by what matters most for your work: Mercury 2 on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceMercury 2Mercury 2 $0.375 · Qwen3.5 9B Base $0.427 · Qwen3.5 35B-A3B Base $0.739 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 9B Base and Qwen3.5 35B-A3B BaseQwen3.5 9B Base 262,144 · Qwen3.5 35B-A3B Base 262,144 · Mercury 2 128,000 tokens
- Widest inputsQwen3.5 9B Base and Qwen3.5 35B-A3B BaseQwen3.5 9B Base: Text, Images, Video · Qwen3.5 35B-A3B Base: Text, Images, Video · Mercury 2: Text
- Self-hostingQwen3.5 9B Base and Qwen3.5 35B-A3B BasePublishes downloadable weights (Apache-2.0)
| Measure | Weight | Qwen3.5 9B Base | Qwen3.5 35B-A3B Base | Mercury 2 |
|---|---|---|---|---|
| Price | 50% | 65 | 54 | 67 |
| Inputs & features | 30% | 35 | 35 | 45 |
| Context window | 20% | 37 | 37 | 24 |
| Overall | 100% | 50/100 | 45/100 | 52/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen3.5 9B BaseAlibaba (Qwen) | Qwen3.5 35B-A3B BaseAlibaba (Qwen) | Mercury 2Inception |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.54 | $0.25 (best) |
| Output | $0.807 | $1.33 | $0.75 (best) |
| Cached input | — | — | $0.025 |
| Blended (3:1) | $0.427 | $0.739 | $0.375 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Official Inception API |
| Limits | |||
| Context window | 262,144 tokens (best) | 262,144 tokens (best) | 128,000 tokens |
| Max output | 65,536 tokens (best) | 65,536 tokens (best) | 50,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | Yes | No |
| Reasoning | No | No | Yeslow · medium · high |
| Tool calling | No | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | OpenApache-2.0 | OpenApache-2.0 | Proprietary |
| API model ID | — | — | mercury-2 |
| API providers | 1 | 1 | 7 (best) |
| Released | Feb 26, 2026 | Feb 24, 2026 | Feb 24, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3.5 9B Base$4.61
- Qwen3.5 35B-A3B Base$8.07
- Mercury 2$4.00
Which should you choose?
Which is better: Qwen3.5 9B Base, Qwen3.5 35B-A3B Base or Mercury 2?
It is close. Our weighted score puts them within 2 points (Mercury 2 52/100, Qwen3.5 9B Base 50/100, Qwen3.5 35B-A3B Base 45/100), so choose by what matters most for your work: Mercury 2 on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Qwen3.5 9B Base, Qwen3.5 35B-A3B Base or Mercury 2?
Mercury 2 is cheaper at $0.25 input / $0.75 output per million tokens (official Inception API price). Qwen3.5 9B Base costs $0.30 input / $0.807 output per million tokens (median across 1 API provider); Qwen3.5 35B-A3B Base costs $0.54 input / $1.33 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.375 per million tokens for Mercury 2 versus $0.427 for Qwen3.5 9B Base (1.1× as much) and $0.739 for Qwen3.5 35B-A3B Base (2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3.5 9B Base has not been scored yet, Qwen3.5 35B-A3B Base has not been scored yet and Mercury 2 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 9B Base, Qwen3.5 35B-A3B Base and Mercury 2 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen3.5 9B Base and Qwen3.5 35B-A3B Base does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 9B Base and Qwen3.5 35B-A3B Base have the largest context windows (262,144 and 262,144 tokens), against 128,000 for Mercury 2. Maximum output per response: Qwen3.5 9B Base up to 65,536, Qwen3.5 35B-A3B Base up to 65,536, Mercury 2 up to 50,000 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 9B Base accepts text, images and video; Qwen3.5 35B-A3B Base accepts text, images and video; Mercury 2 accepts text. Qwen3.5 9B Base handles the widest range of inputs.
Are any of these open source?
Qwen3.5 9B Base and Qwen3.5 35B-A3B Base publishes its weights (Apache-2.0) and can be self-hosted; Mercury 2 is proprietary.
Which is newer?
Qwen3.5 9B Base is the newest, released Feb 26, 2026. Qwen3.5 35B-A3B Base came out Feb 24, 2026; Mercury 2 came out Feb 24, 2026.
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.
