# MiMo-V2.6-Pro vs Qwen3.5-9B

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 33.8 on the Noometry Index. Qwen3.5-9B costs 4.8× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mimo-v2-6-pro-vs-qwen3-5-9b
- Last updated: 2026-10-12
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 4 categories and Qwen3.5-9B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where MiMo-V2.6-Pro leads 37.5 to 14.5.
- The biggest single-benchmark swing is SciCode: 60.9% for MiMo-V2.6-Pro and 27.5% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 50.3 | 33.8 |
| Rank | 49 | 236 |
| Context | 1.05M | 262K |
| Input $/M | $0.43 | $0.10 |
| Output $/M | $0.87 | $0.15 |
| Weights | Open | Open |

## Coding

- MiMo-V2.6-Pro: 55.5 (#23)
- Qwen3.5-9B: 35.9 (#217)

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| SciCode | 60.9% | 27.5% |
| LMArena WebDev | 1629 | — |
| LMArena Coding | 1534 | — |
| ALE-Bench | 1,158 | — |

## Agentic & Tool Use

- MiMo-V2.6-Pro: 37.5 (#35)
- Qwen3.5-9B: 14.5 (#151)

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| APEX-Agents | 59.5% | — |

## Reasoning

- MiMo-V2.6-Pro: 43.1 (#50)
- Qwen3.5-9B: 23.1 (#182)

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| CritPt | 26.6% | 0.3% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | 1512 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
| Epoch Capabilities Index | — | 139.46 |

## Math

- MiMo-V2.6-Pro: 54.5 (#45)
- Qwen3.5-9B: 34.8 (#192)

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 48.5% |
| OTIS Mock AIME 2024-2025 | — | 61.7% |
| ProofBench | 70% | — |
| LMArena Math | 1494 | — |

## Knowledge

- MiMo-V2.6-Pro: 43.5 (#92)
- Qwen3.5-9B: 46.0 (#84)

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | — | 79% |
| LMArena Expert | 1543 | — |

## Multimodal

- MiMo-V2.6-Pro: 40.8 (#43)
- Qwen3.5-9B: —

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| LMArena Vision | 1264 | — |

## Multilingual

- MiMo-V2.6-Pro: 56.9 (#14)
- Qwen3.5-9B: —

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1529 | — |
| LMArena Russian | 1480 | — |

## Instruction Following

- MiMo-V2.6-Pro: 78.2 (#12)
- Qwen3.5-9B: —

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1493 | — |

## Long Context

- MiMo-V2.6-Pro: 46.0 (#27)
- Qwen3.5-9B: —

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1501 | — |

## Writing & Preference

- MiMo-V2.6-Pro: 66.8 (#33)
- Qwen3.5-9B: —

| Benchmark | MiMo-V2.6-Pro | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1492 | — |
| LMArena Creative Writing | 1468 | — |
| LMArena Multi-Turn | 1464 | — |

## FAQ

### Is MiMo-V2.6-Pro better than Qwen3.5-9B?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 33.8 on the Noometry Index. Qwen3.5-9B costs 4.8× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

### Which is cheaper, MiMo-V2.6-Pro or Qwen3.5-9B?

Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

### Is MiMo-V2.6-Pro or Qwen3.5-9B better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 262K.

### How many benchmarks do MiMo-V2.6-Pro and Qwen3.5-9B share?

2 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Qwen3.5-9B has 10.