# DeepSeek LLM 67B vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-mimo-v2-6-pro
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B 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 math, where MiMo-V2.6-Pro leads 54.5 to 8.7.

## Snapshot

| | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 24.9 | 50.3 |
| Rank | 347 | 49 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1096 | 1534 |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| ALE-Bench | — | 1,158 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1512 |
| CritPt | — | 26.6% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1108 | 1494 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| ProofBench | — | 70% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1543 |

## Multimodal

- DeepSeek LLM 67B: —
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1073 | 1474 |
| LMArena Chinese | 1132 | 1529 |
| LMArena Russian | — | 1480 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1079 | 1493 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1092 | 1501 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | DeepSeek LLM 67B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1105 | 1492 |
| LMArena Creative Writing | 1067 | 1468 |
| LMArena Multi-Turn | 1082 | 1464 |

## FAQ

### Is DeepSeek LLM 67B better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and MiMo-V2.6-Pro share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and MiMo-V2.6-Pro has 19.