# Llama 3-70B vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-70b-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.5 leads 35.4 to 12.0.

## Snapshot

| | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 28.5 | 43.0 |
| Rank | 317 | 89 |
| Context | — | 1.05M |
| Input $/M | — | $0.14 |
| Output $/M | — | $0.28 |
| Weights | Open | Open |

## Coding

- Llama 3-70B: 35.3 (#215)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1206 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| ALE-Bench | — | 513.95 |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |

## Agentic & Tool Use

- Llama 3-70B: 20.9 (#132)
- MiMo-V2.5: —

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| Cybench | 5% | — |

## Reasoning

- Llama 3-70B: 17.4 (#284)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1450 |
| Kagi LLM Benchmark | 35.1% | — |
| CritPt | — | 3.7% |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.91 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |

## Math

- Llama 3-70B: 12.0 (#299)
- MiMo-V2.5: 35.4 (#145)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1218 | 1436 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| ProofBench | — | 16% |
| MATH Level 5 | 22.6% | — |

## Knowledge

- Llama 3-70B: 20.8 (#272)
- MiMo-V2.5: 40.2 (#109)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1149 | 1459 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |

## Multimodal

- Llama 3-70B: —
- MiMo-V2.5: 39.0 (#53)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Llama 3-70B: 33.8 (#246)
- MiMo-V2.5: 52.0 (#96)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1142 | 1404 |
| LMArena Chinese | 1114 | 1467 |
| LMArena French | 1231 | 1447 |
| LMArena German | 1169 | 1421 |
| LMArena Japanese | 1017 | 1304 |
| LMArena Korean | 1017 | 1363 |
| LMArena Russian | 1159 | 1395 |
| LMArena Spanish | 1241 | 1412 |

## Instruction Following

- Llama 3-70B: 62.8 (#233)
- MiMo-V2.5: 75.7 (#55)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1194 | 1433 |

## Long Context

- Llama 3-70B: 35.6 (#235)
- MiMo-V2.5: 44.1 (#69)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1174 | 1444 |

## Writing & Preference

- Llama 3-70B: 43.0 (#225)
- MiMo-V2.5: 61.8 (#82)

| Benchmark | Llama 3-70B | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1221 | 1427 |
| LMArena Creative Writing | 1210 | 1392 |
| LMArena Multi-Turn | 1223 | 1445 |

## FAQ

### Is Llama 3-70B better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 28.5 on the Noometry Index.

### Is Llama 3-70B or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 35.3 in the Noometry coding category.

### How many benchmarks do Llama 3-70B and MiMo-V2.5 share?

17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and MiMo-V2.5 has 23.