# Llama 3.2 1B vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.4 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.5× less per token, which makes it the better buy when MiMo-V2.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-3-2-1b-vs-mimo-v2-5
- Last updated: 2026-10-11
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 21.3.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 60K.

## Snapshot

| | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 20.1 | 43.4 |
| Rank | 354 | 93 |
| Context | 60K | 1.05M |
| Input $/M | $0.027 | $0.14 |
| Output $/M | $0.20 | $0.28 |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 21.1 (#338)
- MiMo-V2.5: 43.9 (#81)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1070 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 8.2% | — |
| BigCodeBench Complete | 11.3% | — |
| ALE-Bench | — | 513.95 |

## Agentic & Tool Use

- Llama 3.2 1B: 14.6 (#150)
- MiMo-V2.5: —

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 16.2 (#308)
- MiMo-V2.5: 28.6 (#101)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1450 |
| CritPt | — | 3.7% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 101.99 | — |

## Math

- Llama 3.2 1B: 10.4 (#313)
- MiMo-V2.5: 36.8 (#163)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1086 | 1436 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| ProofBench | — | 16% |

## Knowledge

- Llama 3.2 1B: 7.2 (#312)
- MiMo-V2.5: 40.8 (#115)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1007 | 1460 |
| GPQA Diamond | 23.9% | — |

## Multimodal

- Llama 3.2 1B: —
- MiMo-V2.5: 39.8 (#54)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |

## Multilingual

- Llama 3.2 1B: 23.8 (#292)
- MiMo-V2.5: 51.9 (#99)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 973 | 1404 |
| LMArena Chinese | 959 | 1468 |
| LMArena German | 1014 | 1421 |
| LMArena Russian | 941 | 1395 |
| LMArena French | — | 1447 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Spanish | — | 1416 |

## Instruction Following

- Llama 3.2 1B: 52.4 (#290)
- MiMo-V2.5: 75.5 (#60)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1031 | 1434 |

## Long Context

- Llama 3.2 1B: 31.9 (#274)
- MiMo-V2.5: 44.2 (#73)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1050 | 1445 |

## Writing & Preference

- Llama 3.2 1B: 21.3 (#310)
- MiMo-V2.5: 61.6 (#86)

| Benchmark | Llama 3.2 1B | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1055 | 1428 |
| LMArena Creative Writing | 1033 | 1393 |
| LMArena Multi-Turn | 1030 | 1445 |
| EQ-Bench Creative Writing | 200 | — |

## FAQ

### Is Llama 3.2 1B better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 20.1 on the Noometry Index. Llama 3.2 1B costs 2.5× less per token, which makes it the better buy when MiMo-V2.5's lead doesn't matter for your workload.

### Which is cheaper, Llama 3.2 1B or MiMo-V2.5?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.

### Is Llama 3.2 1B or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 21.1 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 60K.

### How many benchmarks do Llama 3.2 1B and MiMo-V2.5 share?

13 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and MiMo-V2.5 has 23.