# MiMo-V2.5 vs Qwen3.8 27B

> Qwen3.8 27B is the stronger model overall, scoring 46.0 to 43.4 on the Noometry Index. MiMo-V2.5 costs 3.5× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mimo-v2-5-vs-qwen3-8-27b
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. MiMo-V2.5 scores higher in 0 categories and Qwen3.8 27B in 9 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 28.6.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.04 / $2.30 for Qwen3.8 27B.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 43.4 | 46.0 |
| Rank | 93 | 68 |
| Context | 1.05M | 262K |
| Input $/M | $0.14 | $0.04 |
| Output $/M | $0.28 | $2.30 |
| Weights | Open | Open |

## Coding

- MiMo-V2.5: 43.9 (#81)
- Qwen3.8 27B: 50.5 (#44)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | 1438 | 1593 |
| SciCode | 43.1% | 46.6% |
| LMArena Coding | 1469 | 1482 |
| ALE-Bench | 513.95 | — |

## Agentic & Tool Use

- MiMo-V2.5: —
- Qwen3.8 27B: 32.9 (#57)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |

## Reasoning

- MiMo-V2.5: 28.6 (#101)
- Qwen3.8 27B: 41.0 (#54)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| CritPt | 3.7% | 5.4% |
| LMArena Hard Prompts | 1450 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |

## Math

- MiMo-V2.5: 36.8 (#163)
- Qwen3.8 27B: 37.1 (#161)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| ProofBench | 16% | 16% |
| LMArena Math | 1436 | 1456 |

## Knowledge

- MiMo-V2.5: 40.8 (#115)
- Qwen3.8 27B: 41.6 (#109)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1460 | 1482 |

## Multimodal

- MiMo-V2.5: 39.8 (#54)
- Qwen3.8 27B: 41.3 (#37)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | 1247 | 1271 |

## Multilingual

- MiMo-V2.5: 51.9 (#99)
- Qwen3.8 27B: 53.7 (#60)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1404 | 1430 |
| LMArena Chinese | 1468 | 1504 |
| LMArena French | 1447 | 1465 |
| LMArena German | 1421 | 1438 |
| LMArena Japanese | 1306 | 1384 |
| LMArena Korean | 1363 | 1393 |
| LMArena Russian | 1395 | 1415 |
| LMArena Spanish | 1416 | 1448 |

## Instruction Following

- MiMo-V2.5: 75.5 (#60)
- Qwen3.8 27B: 75.8 (#53)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1439 |

## Long Context

- MiMo-V2.5: 44.2 (#73)
- Qwen3.8 27B: 44.3 (#70)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1445 | 1450 |

## Writing & Preference

- MiMo-V2.5: 61.6 (#86)
- Qwen3.8 27B: 65.8 (#43)

| Benchmark | MiMo-V2.5 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1428 | 1441 |
| LMArena Creative Writing | 1393 | 1384 |
| LMArena Multi-Turn | 1445 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |

## FAQ

### Is MiMo-V2.5 better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 46.0 to 43.4 on the Noometry Index. MiMo-V2.5 costs 3.5× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.

### Which is cheaper, MiMo-V2.5 or Qwen3.8 27B?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen3.8 27B lists at $0.04 and $2.30.

### Is MiMo-V2.5 or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 43.9 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 262K.

### How many benchmarks do MiMo-V2.5 and Qwen3.8 27B share?

22 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Qwen3.8 27B has 31.