MiMo-V2-Pro vs Qwen3.5 9B Base vs Grok 4.20 (Non-Reasoning)
Too close to call on our weighted score (Grok 4.20 (Non-Reasoning) 52, Qwen3.5 9B Base 50, MiMo-V2-Pro 42). The right pick depends on what you value most.
XiaomiMiMo-V2-Pro
42/100- ECI—
- Price$1.00 / $3.00
- Context1.05M
Alibaba (Qwen)Qwen3.5 9B Base
50/100- ECI—
- Price$0.30 / $0.807
- Context262K
xAIGrok 4.20 (Non-Reasoning)
52/100- ECI—
- Price$1.25 / $2.50
- Context1M
Too close to call
It is close. Our weighted score puts them within 2 points (Grok 4.20 (Non-Reasoning) 52/100, Qwen3.5 9B Base 50/100, MiMo-V2-Pro 42/100), so choose by what matters most for your work: Qwen3.5 9B Base on price and MiMo-V2-Pro for long inputs. 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 priceQwen3.5 9B BaseQwen3.5 9B Base $0.427 · MiMo-V2-Pro $1.50 · Grok 4.20 (Non-Reasoning) $1.56 per 1M tokens (3:1 blend)
- Longest contextMiMo-V2-ProMiMo-V2-Pro 1,048,576 · Grok 4.20 (Non-Reasoning) 1,000,000 · Qwen3.5 9B Base 262,144 tokens
- Widest inputsQwen3.5 9B Base and Grok 4.20 (Non-Reasoning)MiMo-V2-Pro: Text · Qwen3.5 9B Base: Text, Images, Video · Grok 4.20 (Non-Reasoning): Text, Images, PDFs
- Self-hostingQwen3.5 9B BasePublishes downloadable weights (Apache-2.0)
| Measure | Weight | MiMo-V2-Pro | Qwen3.5 9B Base | Grok 4.20 (Non-Reasoning) |
|---|---|---|---|---|
| Price | 50% | 40 | 65 | 39 |
| Inputs & features | 30% | 35 | 35 | 70 |
| Context window | 20% | 61 | 37 | 60 |
| Overall | 100% | 42/100 | 50/100 | 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 | MiMo-V2-ProXiaomi | Qwen3.5 9B BaseAlibaba (Qwen) | Grok 4.20 (Non-Reasoning)xAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.00 | $0.30 (best) | $1.25 |
| Output | $3.00 | $0.807 (best) | $2.50 |
| Cached input | — | — | $0.20 |
| Blended (3:1) | $1.50 | $0.427 (best) | $1.56 |
| Long-context rate | Same rate | Same rate | Over 200K: $2.50 / $5.00 |
| Price source | Median of 1 providers | Median of 1 providers | Official xAI API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 1,000,000 tokens |
| Max output | 131,072 tokens (best) | 65,536 tokens | 30,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | Proprietary |
| API model ID | — | — | grok-4.20-0309-non-reasoning |
| API providers | 2 | 1 | 13 (best) |
| Released | Mar 18, 2026 | Feb 26, 2026 | Mar 9, 2026 |
| Knowledge cutoff | Dec 2024 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiMo-V2-Pro$16.00
- Qwen3.5 9B Base$4.61
- Grok 4.20 (Non-Reasoning)$17.50
Which should you choose?
Which is better: MiMo-V2-Pro, Qwen3.5 9B Base or Grok 4.20 (Non-Reasoning)?
It is close. Our weighted score puts them within 2 points (Grok 4.20 (Non-Reasoning) 52/100, Qwen3.5 9B Base 50/100, MiMo-V2-Pro 42/100), so choose by what matters most for your work: Qwen3.5 9B Base on price and MiMo-V2-Pro for long inputs. 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, MiMo-V2-Pro, Qwen3.5 9B Base or Grok 4.20 (Non-Reasoning)?
Qwen3.5 9B Base is cheaper at $0.30 input / $0.807 output per million tokens (median across 1 API provider). MiMo-V2-Pro costs $1.00 input / $3.00 output per million tokens (median across 1 API provider); Grok 4.20 (Non-Reasoning) costs $1.25 input / $2.50 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.427 per million tokens for Qwen3.5 9B Base versus $1.50 for MiMo-V2-Pro (3.5× as much) and $1.56 for Grok 4.20 (Non-Reasoning) (3.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiMo-V2-Pro has not been scored yet, Qwen3.5 9B Base has not been scored yet and Grok 4.20 (Non-Reasoning) has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiMo-V2-Pro, Qwen3.5 9B Base and Grok 4.20 (Non-Reasoning) 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?
MiMo-V2-Pro has the largest context window at 1,048,576 tokens, against 1,000,000 for Grok 4.20 (Non-Reasoning) and 262,144 for Qwen3.5 9B Base. Maximum output per response: MiMo-V2-Pro up to 131,072, Qwen3.5 9B Base up to 65,536, Grok 4.20 (Non-Reasoning) up to 30,000 tokens.
Which can read images, PDFs, audio or video?
MiMo-V2-Pro accepts text; Qwen3.5 9B Base accepts text, images and video; Grok 4.20 (Non-Reasoning) accepts text, images and PDFs. Qwen3.5 9B Base handles the widest range of inputs.
Are any of these open source?
Qwen3.5 9B Base publishes its weights (Apache-2.0) and can be self-hosted; MiMo-V2-Pro and Grok 4.20 (Non-Reasoning) is proprietary.
Which is newer?
MiMo-V2-Pro is the newest, released Mar 18, 2026. Grok 4.20 (Non-Reasoning) came out Mar 9, 2026; Qwen3.5 9B Base came out Feb 26, 2026. Knowledge cutoff: MiMo-V2-Pro Dec 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.
