# Llama 3.2 90B vs MiMo-V2.5-Pro

> MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-mimo-v2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where MiMo-V2.5-Pro leads 38.6 to 10.4.

## Snapshot

| | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 27.1 | 44.8 |
| Rank | 326 | 70 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Open | Open |

## Coding

- Llama 3.2 90B: —
- MiMo-V2.5-Pro: 47.0 (#58)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| LMArena Coding | — | 1502 |
| ALE-Bench | — | 899.8 |

## Agentic & Tool Use

- Llama 3.2 90B: 29.7 (#73)
- MiMo-V2.5-Pro: —

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 20.9 (#207)
- MiMo-V2.5-Pro: 25.9 (#124)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1487 |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 10.4 (#302)
- MiMo-V2.5-Pro: 38.6 (#84)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| ProofBench | — | 22% |
| LMArena Math | — | 1480 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#269)
- MiMo-V2.5-Pro: 41.5 (#100)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1501 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 24.9 (#119)
- MiMo-V2.5-Pro: —

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- MiMo-V2.5-Pro: 55.3 (#33)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | — | 1449 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1489 |
| LMArena German | — | 1455 |
| LMArena Japanese | — | 1418 |
| LMArena Korean | — | 1436 |
| LMArena Russian | — | 1450 |
| LMArena Spanish | — | 1470 |

## Instruction Following

- Llama 3.2 90B: —
- MiMo-V2.5-Pro: 77.6 (#21)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1477 |

## Long Context

- Llama 3.2 90B: —
- MiMo-V2.5-Pro: 45.4 (#38)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | — | 1482 |

## Writing & Preference

- Llama 3.2 90B: —
- MiMo-V2.5-Pro: 65.5 (#47)

| Benchmark | Llama 3.2 90B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | — | 1465 |
| LMArena Creative Writing | — | 1440 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
| LMArena Multi-Turn | — | 1477 |

## FAQ

### Is Llama 3.2 90B better than MiMo-V2.5-Pro?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 27.1 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and MiMo-V2.5-Pro share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and MiMo-V2.5-Pro has 27.