# DeepSeek-V2.5 (Sep 2024) vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 37.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and MiMo-V2.6-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 31.7.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 37.6 | 50.3 |
| Rank | 200 | 49 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1309 | 1534 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,158 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1512 |
| CritPt | — | 26.6% |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1288 | 1494 |
| ProofBench | — | 70% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1266 | 1543 |

## Multimodal

- DeepSeek-V2.5 (Sep 2024): —
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1273 | 1474 |
| LMArena Chinese | 1318 | 1529 |
| LMArena Russian | 1289 | 1480 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1280 | 1493 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1301 | 1501 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1294 | 1492 |
| LMArena Creative Writing | 1285 | 1468 |
| LMArena Multi-Turn | 1297 | 1464 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 37.6 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiMo-V2.6-Pro share?

12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiMo-V2.6-Pro has 19.