# Llama 3.2 3B vs Mistral 7B

> Llama 3.2 3B is the stronger model overall, scoring 28.9 to 23.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-3b-vs-mistral-7b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Llama 3.2 3B scores higher in 7 categories and Mistral 7B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.2 3B leads 32.4 to 8.1.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- Llama 3.2 3B accepts more context: 131K tokens versus 8K.

## Snapshot

| | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.9 | 23.0 |
| Rank | 321 | 351 |
| Context | 131K | 8K |
| Input $/M | $0.05 | $0.25 |
| Output $/M | $0.33 | $0.25 |
| Weights | Open | Open |

## Coding

- Llama 3.2 3B: 27.6 (#319)
- Mistral 7B: 26.4 (#326)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | 23.4% | 19.5% |
| LMArena Coding | 1098 | 1082 |
| BigCodeBench Complete | 28.3% | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |

## Agentic & Tool Use

- Llama 3.2 3B: 20.1 (#143)
- Mistral 7B: —

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |

## Reasoning

- Llama 3.2 3B: 21.0 (#228)
- Mistral 7B: 13.1 (#336)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1067 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |

## Math

- Llama 3.2 3B: 32.4 (#214)
- Mistral 7B: 8.1 (#325)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Math | 1126 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |

## Knowledge

- Llama 3.2 3B: 29.7 (#235)
- Mistral 7B: 7.4 (#311)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Expert | 1090 | 1036 |
| GPQA Diamond | — | 15.2% |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |

## Multilingual

- Llama 3.2 3B: 26.2 (#281)
- Mistral 7B: 25.8 (#283)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1019 | 1012 |
| LMArena Chinese | 1017 | 1009 |
| LMArena German | 1056 | 987 |
| LMArena Russian | 949 | 1018 |
| LMArena French | — | 1037 |
| LMArena Japanese | — | 878 |
| LMArena Spanish | — | 1026 |

## Instruction Following

- Llama 3.2 3B: 56.0 (#275)
- Mistral 7B: 54.2 (#280)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1089 | 1060 |

## Long Context

- Llama 3.2 3B: 33.4 (#261)
- Mistral 7B: 32.2 (#271)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1100 | 1060 |

## Writing & Preference

- Llama 3.2 3B: 24.7 (#307)
- Mistral 7B: 30.7 (#286)

| Benchmark | Llama 3.2 3B | Mistral 7B |
|---|---|---|
| LMArena Text | 1110 | 1090 |
| LMArena Creative Writing | 1094 | 1068 |
| LMArena Multi-Turn | 1105 | 1062 |
| EQ-Bench Creative Writing | 595 | — |

## FAQ

### Is Llama 3.2 3B better than Mistral 7B?

Llama 3.2 3B is the stronger model overall, scoring 28.9 to 23.0 on the Noometry Index.

### Which is cheaper, Llama 3.2 3B or Mistral 7B?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

### Is Llama 3.2 3B or Mistral 7B better for coding?

Llama 3.2 3B scores higher on coding benchmarks: 27.6 versus 26.4 in the Noometry coding category.

### Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 8K.

### How many benchmarks do Llama 3.2 3B and Mistral 7B share?

15 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Mistral 7B has 37.