# Codellama 70b Instruct vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.4 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-mimo-v2-5
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and MiMo-V2.5 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 33.4.

## Snapshot

| | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 33.7 | 43.4 |
| Rank | 237 | 93 |
| Context | — | 1.05M |
| Input $/M | — | $0.14 |
| Output $/M | — | $0.28 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- MiMo-V2.5: 43.9 (#81)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1469 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 513.95 |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- MiMo-V2.5: 28.6 (#101)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1450 |
| CritPt | — | 3.7% |

## Math

- Codellama 70b Instruct: —
- MiMo-V2.5: 36.8 (#163)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1436 |

## Knowledge

- Codellama 70b Instruct: —
- MiMo-V2.5: 40.8 (#115)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | — | 1460 |

## Multimodal

- Codellama 70b Instruct: —
- MiMo-V2.5: 39.8 (#54)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- MiMo-V2.5: 51.9 (#99)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 992 | 1404 |
| LMArena Chinese | — | 1468 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1416 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- MiMo-V2.5: 75.5 (#60)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1434 |

## Long Context

- Codellama 70b Instruct: —
- MiMo-V2.5: 44.2 (#73)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | — | 1445 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- MiMo-V2.5: 61.6 (#86)

| Benchmark | Codellama 70b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1057 | 1428 |
| LMArena Creative Writing | — | 1393 |
| LMArena Multi-Turn | — | 1445 |

## FAQ

### Is Codellama 70b Instruct better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and MiMo-V2.5 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and MiMo-V2.5 has 23.