# Claude 3 Sonnet vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and MiMo-V2.5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.5 leads 36.8 to 10.7.
- MiMo-V2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 29.0 | 43.4 |
| Rank | 319 | 93 |
| Context | — | 1.05M |
| Input $/M | — | $0.14 |
| Output $/M | — | $0.28 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.6 (#302)
- MiMo-V2.5: 43.9 (#81)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1223 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 513.95 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Reasoning

- Claude 3 Sonnet: 20.5 (#237)
- MiMo-V2.5: 28.6 (#101)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1450 |
| CritPt | — | 3.7% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.7 (#310)
- MiMo-V2.5: 36.8 (#163)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1213 | 1436 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| ProofBench | — | 16% |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#276)
- MiMo-V2.5: 40.8 (#115)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1173 | 1460 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 25.2 (#125)
- MiMo-V2.5: 39.8 (#54)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 984 | 1247 |

## Multilingual

- Claude 3 Sonnet: 37.8 (#234)
- MiMo-V2.5: 51.9 (#99)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1205 | 1404 |
| LMArena Chinese | 1189 | 1468 |
| LMArena French | 1229 | 1447 |
| LMArena German | 1204 | 1421 |
| LMArena Japanese | 1131 | 1306 |
| LMArena Korean | 1128 | 1363 |
| LMArena Russian | 1227 | 1395 |
| LMArena Spanish | 1204 | 1416 |

## Instruction Following

- Claude 3 Sonnet: 62.8 (#235)
- MiMo-V2.5: 75.5 (#60)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1434 |

## Long Context

- Claude 3 Sonnet: 36.7 (#228)
- MiMo-V2.5: 44.2 (#73)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1211 | 1445 |

## Writing & Preference

- Claude 3 Sonnet: 42.1 (#238)
- MiMo-V2.5: 61.6 (#86)

| Benchmark | Claude 3 Sonnet | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1218 | 1428 |
| LMArena Creative Writing | 1186 | 1393 |
| LMArena Multi-Turn | 1227 | 1445 |

## FAQ

### Is Claude 3 Sonnet better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.0 on the Noometry Index.

### Is Claude 3 Sonnet or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 29.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and MiMo-V2.5 share?

18 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and MiMo-V2.5 has 23.