Qwen3.5 9B Base vs Mistral Small 4 vs Mercury 2
Mistral Small 4 comes out ahead, 65 to 52 and 50 on our weighted score, and it is the cheaper option too.
Alibaba (Qwen)Qwen3.5 9B Base
50/100- ECI—
- Price$0.30 / $0.807
- Context262K
- Our pick
Mistral AIMistral Small 4
65/100- ECI—
- Price$0.15 / $0.60
- Context256K
InceptionMercury 2
52/100- ECI—
- Price$0.25 / $0.75
- Context128K
Mistral Small 4 is our pick
Mistral Small 4 is the better all-round choice, scoring 65/100 against Mercury 2 (52) and Qwen3.5 9B Base (50). It leads on price and inputs & features. 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 priceMistral Small 4Mistral Small 4 $0.263 · Mercury 2 $0.375 · Qwen3.5 9B Base $0.427 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 9B BaseQwen3.5 9B Base 262,144 · Mistral Small 4 256,000 · Mercury 2 128,000 tokens
- Widest inputsQwen3.5 9B BaseQwen3.5 9B Base: Text, Images, Video · Mistral Small 4: Text, Images · Mercury 2: Text
- Self-hostingQwen3.5 9B Base and Mistral Small 4Publishes downloadable weights (Apache-2.0)
| Measure | Weight | Qwen3.5 9B Base | Mistral Small 4 | Mercury 2 |
|---|---|---|---|---|
| Price | 50% | 65 | 74 | 67 |
| Inputs & features | 30% | 35 | 70 | 45 |
| Context window | 20% | 37 | 36 | 24 |
| Overall | 100% | 50/100 | 65/100 | 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) | Mistral Small 4Mistral AI | Mercury 2Inception |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.15 (best) | $0.25 |
| Output | $0.807 | $0.60 (best) | $0.75 |
| Cached input | — | $0.015 (best) | $0.025 |
| Blended (3:1) | $0.427 | $0.263 (best) | $0.375 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official Mistral API | Official Inception API |
| Limits | |||
| Context window | 262,144 tokens (best) | 256,000 tokens | 128,000 tokens |
| Max output | 65,536 tokens | 256,000 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 | No | No |
| Reasoning | No | Yeshigh | Yeslow · medium · high |
| Tool calling | No | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Proprietary |
| API model ID | — | mistral-small-2603 | mercury-2 |
| API providers | 1 | 21 (best) | 7 |
| Released | Feb 26, 2026 | Mar 16, 2026 | Feb 24, 2026 |
| Knowledge cutoff | — | Jun 2025 | — |
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
- Mistral Small 4$2.70
- Mercury 2$4.00
Which should you choose?
Which is better: Qwen3.5 9B Base, Mistral Small 4 or Mercury 2?
Mistral Small 4 is the better all-round choice, scoring 65/100 against Mercury 2 (52) and Qwen3.5 9B Base (50). It leads on price and inputs & features. 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, Mistral Small 4 or Mercury 2?
Mistral Small 4 is cheaper at $0.15 input / $0.60 output per million tokens (official Mistral API price). Mercury 2 costs $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). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Mistral Small 4 versus $0.375 for Mercury 2 (1.4× as much) and $0.427 for Qwen3.5 9B Base (1.6× 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, Mistral Small 4 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, Mistral Small 4 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 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 9B Base has the largest context window at 262,144 tokens, against 256,000 for Mistral Small 4 and 128,000 for Mercury 2. Maximum output per response: Qwen3.5 9B Base up to 65,536, Mistral Small 4 up to 256,000, Mercury 2 up to 50,000 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 9B Base accepts text, images and video; Mistral Small 4 accepts text and images; 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 Mistral Small 4 publishes its weights (Apache-2.0) and can be self-hosted; Mercury 2 is proprietary.
Which is newer?
Mistral Small 4 is the newest, released Mar 16, 2026. Qwen3.5 9B Base came out Feb 26, 2026; Mercury 2 came out Feb 24, 2026. Knowledge cutoff: Mistral Small 4 Jun 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 Nov 2, 2026.
