# Deepseek Coder v2 vs MiMo-V2-Pro

> MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-mimo-v2-pro
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and MiMo-V2-Pro in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 35.9 | 43.0 |
| Rank | 220 | 103 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Open | Proprietary |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- MiMo-V2-Pro: 43.8 (#83)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1251 | 1476 |
| LMArena WebDev | — | 1433 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 785.17 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- MiMo-V2-Pro: 22.1 (#206)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- MiMo-V2-Pro: 39.5 (#102)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1241 | 1447 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- MiMo-V2-Pro: 41.4 (#111)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1181 | 1478 |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- MiMo-V2-Pro: 52.7 (#81)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1182 | 1416 |
| LMArena Chinese | 1201 | 1456 |
| LMArena French | 1185 | 1469 |
| LMArena German | 1164 | 1417 |
| LMArena Japanese | 1126 | 1366 |
| LMArena Korean | 1104 | 1400 |
| LMArena Russian | 1188 | 1427 |
| LMArena Spanish | 1153 | 1457 |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- MiMo-V2-Pro: 76.0 (#49)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1180 | 1445 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- MiMo-V2-Pro: 41.5 (#138)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1219 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- MiMo-V2-Pro: 62.8 (#70)

| Benchmark | Deepseek Coder v2 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1191 | 1436 |
| LMArena Creative Writing | 1120 | 1415 |
| LMArena Multi-Turn | 1177 | 1456 |

## FAQ

### Is Deepseek Coder v2 better than MiMo-V2-Pro?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 35.9 on the Noometry Index.

### Is Deepseek Coder v2 or MiMo-V2-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 38.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and MiMo-V2-Pro share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and MiMo-V2-Pro has 23.