# Llama 2-13B vs Mistral Small 3

> Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-13b-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Llama 2-13B scores higher in 2 categories and Mistral Small 3 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 31.1 to 16.3.

## Snapshot

| | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 31.2 |
| Rank | 309 | 278 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Llama 2-13B: 30.9 (#291)
- Mistral Small 3: 36.5 (#207)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1062 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Reasoning

- Llama 2-13B: 12.8 (#337)
- Mistral Small 3: 18.9 (#273)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1051 | 1233 |
| Epoch Capabilities Index | 106.17 | 127.07 |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |

## Math

- Llama 2-13B: 31.1 (#229)
- Mistral Small 3: 16.3 (#295)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1065 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| GSM8K | 36.9% | — |

## Knowledge

- Llama 2-13B: 28.1 (#249)
- Mistral Small 3: 25.1 (#263)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1030 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |

## Multimodal

- Llama 2-13B: —
- Mistral Small 3: —

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| ScienceQA | 55.8% | — |

## Multilingual

- Llama 2-13B: 26.5 (#279)
- Mistral Small 3: 37.3 (#236)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1024 | 1198 |
| LMArena Chinese | 1001 | 1204 |
| LMArena French | 1044 | 1203 |
| LMArena German | 1009 | 1211 |
| LMArena Japanese | 894 | 1111 |
| LMArena Korean | 953 | 1188 |
| LMArena Russian | 1055 | 1216 |
| LMArena Spanish | 1087 | — |

## Instruction Following

- Llama 2-13B: 53.3 (#287)
- Mistral Small 3: 63.7 (#229)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1045 | 1214 |

## Long Context

- Llama 2-13B: 32.3 (#269)
- Mistral Small 3: 37.8 (#211)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1064 | 1246 |

## Writing & Preference

- Llama 2-13B: 29.8 (#289)
- Mistral Small 3: 32.2 (#280)

| Benchmark | Llama 2-13B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1084 | 1234 |
| LMArena Creative Writing | 1047 | 1195 |
| LMArena Multi-Turn | 1050 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Llama 2-13B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.6 on the Noometry Index.

### Is Llama 2-13B or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 30.9 in the Noometry coding category.

### How many benchmarks do Llama 2-13B and Mistral Small 3 share?

18 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Mistral Small 3 has 24.