# DeepSeek-V2 (MoE-236B, May 2024) vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro has enough public results to be ranked (#55); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where MiMo-V2.6-Pro leads 53.2 to 39.8.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 39.7 | 46.7 |
| Rank | — | 55 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
- MiMo-V2.6-Pro: 53.2 (#27)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | — | 1618 |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1538 |
| BigCodeBench Complete | 59.4% | — |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 30.4 (#76)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | — | 1511 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 37.9 (#91)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | — | 1497 |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 43.0 (#85)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | — | 1548 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multimodal

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 40.2 (#40)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1265 |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 57.0 (#15)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | — | 1474 |
| LMArena Chinese | — | 1532 |
| LMArena Russian | — | 1481 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 78.2 (#10)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1490 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 46.0 (#26)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | — | 1500 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- MiMo-V2.6-Pro: 66.9 (#32)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | — | 1491 |
| LMArena Creative Writing | — | 1465 |
| LMArena Multi-Turn | — | 1463 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro has enough public results to be ranked (#55); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 39.8 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and MiMo-V2.6-Pro share?

0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and MiMo-V2.6-Pro has 14.