# Llama 3.2 1B vs Mistral Small 3.2

> Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 20.1 on the Noometry Index. Llama 3.2 1B costs 1.9× less per token, which makes it the better buy when Mistral Small 3.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-3-2-1b-vs-mistral-small-3-2
- Last updated: 2026-10-12
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Mistral Small 3.2 in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small 3.2 leads 45.0 to 21.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Llama 3.2 1B and 30.3% for Mistral Small 3.2.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.0938 / $0.25 for Mistral Small 3.2.
- Mistral Small 3.2 accepts more context: 256K tokens versus 60K.

## Snapshot

| | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 20.1 | 31.2 |
| Rank | 354 | 280 |
| Context | 60K | 256K |
| Input $/M | $0.027 | $0.0938 |
| Output $/M | $0.20 | $0.25 |
| Weights | Open | Open |

## Coding

- Llama 3.2 1B: 21.1 (#338)
- Mistral Small 3.2: —

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| BigCodeBench Instruct | 8.2% | — |
| LMArena Coding | 1070 | — |
| BigCodeBench Complete | 11.3% | — |

## Agentic & Tool Use

- Llama 3.2 1B: 14.6 (#150)
- Mistral Small 3.2: —

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |

## Reasoning

- Llama 3.2 1B: 16.2 (#308)
- Mistral Small 3.2: 18.1 (#287)

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| Chess Puzzles | 0% | 1% |
| Epoch Capabilities Index | 101.99 | 131.74 |
| Kagi LLM Benchmark | — | 40.4% |
| LMArena Hard Prompts | 1044 | — |

## Math

- Llama 3.2 1B: 10.4 (#313)
- Mistral Small 3.2: 26.3 (#260)

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 30.3% |
| LMArena Math | 1086 | — |

## Knowledge

- Llama 3.2 1B: 7.2 (#312)
- Mistral Small 3.2: 26.7 (#256)

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| GPQA Diamond | 23.9% | 49.1% |
| LMArena Expert | 1007 | — |

## Multilingual

- Llama 3.2 1B: 23.8 (#292)
- Mistral Small 3.2: —

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| LMArena Non-English | 973 | — |
| LMArena Chinese | 959 | — |
| LMArena German | 1014 | — |
| LMArena Russian | 941 | — |

## Instruction Following

- Llama 3.2 1B: 52.4 (#290)
- Mistral Small 3.2: —

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| LMArena Instruction Following | 1031 | — |

## Long Context

- Llama 3.2 1B: 31.9 (#274)
- Mistral Small 3.2: —

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| LMArena Longer Query | 1050 | — |

## Writing & Preference

- Llama 3.2 1B: 21.3 (#310)
- Mistral Small 3.2: 45.0 (#224)

| Benchmark | Llama 3.2 1B | Mistral Small 3.2 |
|---|---|---|
| EQ-Bench Creative Writing | 200 | 1255 |
| LMArena Text | 1055 | — |
| LMArena Creative Writing | 1033 | — |
| LMArena Multi-Turn | 1030 | — |

## FAQ

### Is Llama 3.2 1B better than Mistral Small 3.2?

Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 20.1 on the Noometry Index. Llama 3.2 1B costs 1.9× less per token, which makes it the better buy when Mistral Small 3.2's lead doesn't matter for your workload.

### Which is cheaper, Llama 3.2 1B or Mistral Small 3.2?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Mistral Small 3.2 lists at $0.0938 and $0.25.

### Which has the bigger context window?

Mistral Small 3.2 does, with 256K tokens against 60K.

### How many benchmarks do Llama 3.2 1B and Mistral Small 3.2 share?

5 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Mistral Small 3.2 has 6.