# MiMo-V2-Pro vs Qwen3.5 35B-A3B

> MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 42.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-pro-vs-qwen3-5-35b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiMo-V2-Pro scores higher in 4 categories and Qwen3.5 35B-A3B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2-Pro leads 43.8 to 33.8.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 262K.
- Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.0 | 42.0 |
| Rank | 103 | 123 |
| Context | 1.05M | 262K |
| Input $/M | $0.43 | $0.25 |
| Output $/M | $0.87 | $2 |
| Weights | Proprietary | Open |

## Coding

- MiMo-V2-Pro: 43.8 (#83)
- Qwen3.5 35B-A3B: 33.8 (#251)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena WebDev | 1433 | 1254 |
| LMArena Coding | 1476 | 1410 |
| SciCode | — | 29.3% |
| ALE-Bench | 785.17 | — |

## Reasoning

- MiMo-V2-Pro: 22.1 (#206)
- Qwen3.5 35B-A3B: 24.6 (#161)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1400 |
| NYT Connections (extended) | 25.8% | — |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| Thematic Generalization | 45.9% | — |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |

## Math

- MiMo-V2-Pro: 39.5 (#102)
- Qwen3.5 35B-A3B: 39.9 (#97)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1447 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |

## Knowledge

- MiMo-V2-Pro: 41.4 (#111)
- Qwen3.5 35B-A3B: 47.8 (#79)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Expert | 1478 | 1408 |
| GPQA Diamond | — | 83.5% |
| Vectara Hallucination Rate | — | 10.5% |

## Multilingual

- MiMo-V2-Pro: 52.7 (#81)
- Qwen3.5 35B-A3B: 50.0 (#127)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1416 | 1378 |
| LMArena Chinese | 1456 | 1457 |
| LMArena French | 1469 | 1412 |
| LMArena German | 1417 | 1367 |
| LMArena Japanese | 1366 | 1325 |
| LMArena Korean | 1400 | 1356 |
| LMArena Russian | 1427 | 1376 |
| LMArena Spanish | 1457 | 1392 |

## Instruction Following

- MiMo-V2-Pro: 76.0 (#49)
- Qwen3.5 35B-A3B: 72.8 (#128)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1445 | 1379 |

## Long Context

- MiMo-V2-Pro: 41.5 (#138)
- Qwen3.5 35B-A3B: 42.4 (#127)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1455 | 1389 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |

## Writing & Preference

- MiMo-V2-Pro: 62.8 (#70)
- Qwen3.5 35B-A3B: 57.9 (#124)

| Benchmark | MiMo-V2-Pro | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1436 | 1395 |
| LMArena Creative Writing | 1415 | 1346 |
| LMArena Multi-Turn | 1456 | 1390 |

## FAQ

### Is MiMo-V2-Pro better than Qwen3.5 35B-A3B?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 42.0 on the Noometry Index.

### Which is cheaper, MiMo-V2-Pro or Qwen3.5 35B-A3B?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.

### Is MiMo-V2-Pro or Qwen3.5 35B-A3B better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do MiMo-V2-Pro and Qwen3.5 35B-A3B share?

18 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen3.5 35B-A3B has 28.