# Hy3 vs MiMo-V2.5

> Hy3 and MiMo-V2.5 score almost the same on the Noometry Index (44.2 vs 43.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/hy3-vs-mimo-v2-5
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Hy3 scores higher in 4 categories and MiMo-V2.5 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 36.8.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.13 / $0.53 for Hy3.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | Hy3 | MiMo-V2.5 |
|---|---|---|
| Provider | Tencent | Xiaomi |
| Noometry Index | 44.2 | 43.4 |
| Rank | 79 | 93 |
| Context | 262K | 1.05M |
| Input $/M | $0.13 | $0.14 |
| Output $/M | $0.53 | $0.28 |
| Weights | Open | Open |

## Coding

- Hy3: 46.8 (#63)
- MiMo-V2.5: 43.9 (#81)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1508 | 1438 |
| LMArena Coding | 1464 | 1469 |
| SciCode | — | 43.1% |
| ALE-Bench | — | 513.95 |

## Reasoning

- Hy3: 26.1 (#136)
- MiMo-V2.5: 28.6 (#101)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1450 |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 3.7% |

## Math

- Hy3: 40.1 (#93)
- MiMo-V2.5: 36.8 (#163)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1475 | 1436 |
| ProofBench | — | 16% |

## Knowledge

- Hy3: 40.8 (#114)
- MiMo-V2.5: 40.8 (#115)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1460 | 1460 |

## Multimodal

- Hy3: —
- MiMo-V2.5: 39.8 (#54)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |

## Multilingual

- Hy3: 53.5 (#65)
- MiMo-V2.5: 51.9 (#99)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1426 | 1404 |
| LMArena Chinese | 1493 | 1468 |
| LMArena French | 1461 | 1447 |
| LMArena German | 1439 | 1421 |
| LMArena Japanese | 1392 | 1306 |
| LMArena Korean | 1395 | 1363 |
| LMArena Russian | 1432 | 1395 |
| LMArena Spanish | 1456 | 1416 |

## Instruction Following

- Hy3: 75.1 (#70)
- MiMo-V2.5: 75.5 (#60)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1434 |

## Long Context

- Hy3: 44.1 (#75)
- MiMo-V2.5: 44.2 (#73)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1442 | 1445 |

## Writing & Preference

- Hy3: 62.2 (#81)
- MiMo-V2.5: 61.6 (#86)

| Benchmark | Hy3 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1439 | 1428 |
| LMArena Creative Writing | 1402 | 1393 |
| LMArena Multi-Turn | 1436 | 1445 |

## FAQ

### Is Hy3 better than MiMo-V2.5?

Hy3 and MiMo-V2.5 score almost the same on the Noometry Index (44.2 vs 43.4), so choose on price, context window or the category you care about most.

### Which is cheaper, Hy3 or MiMo-V2.5?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Hy3 lists at $0.13 and $0.53.

### Is Hy3 or MiMo-V2.5 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 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 Hy3 and MiMo-V2.5 share?

18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and MiMo-V2.5 has 23.