# Llama 3-8B vs Mistral Small 3

> Mistral Small 3 is the stronger model overall, scoring 30.9 to 25.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-8b-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Llama 3-8B scores higher in 1 category and Mistral Small 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small 3 leads 25.0 to 7.8.
- The biggest single-benchmark swing is GPQA Diamond: 26.1% for Llama 3-8B and 47.3% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.14 / $0.14 for Llama 3-8B.
- Mistral Small 3 accepts more context: 33K tokens versus 8K.

## Snapshot

| | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.3 | 30.9 |
| Rank | 338 | 268 |
| Context | 8K | 33K |
| Input $/M | $0.14 | $0.05 |
| Output $/M | $0.14 | $0.08 |
| Weights | Open | Open |

## Coding

- Llama 3-8B: 30.5 (#285)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 45.3% |
| LMArena Coding | 1152 | 1246 |
| BigCodeBench Complete | 36.9% | 50.4% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |

## Reasoning

- Llama 3-8B: 13.8 (#321)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1133 | 1233 |
| Epoch Capabilities Index | 116.33 | 127.06 |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |

## Math

- Llama 3-8B: 8.3 (#317)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | 6.7% |
| LMArena Math | 1151 | 1240 |
| MATH Level 5 | 6.1% | — |

## Knowledge

- Llama 3-8B: 7.8 (#303)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 26.1% | 47.3% |
| LMArena Expert | 1113 | 1202 |
| Confabulations | — | 25.2% |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |

## Multilingual

- Llama 3-8B: 31.0 (#256)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1098 | 1198 |
| LMArena Chinese | 1076 | 1204 |
| LMArena French | 1158 | 1202 |
| LMArena German | 1104 | 1211 |
| LMArena Japanese | 967 | 1111 |
| LMArena Korean | 1003 | 1188 |
| LMArena Russian | 1109 | 1216 |
| LMArena Spanish | 1172 | — |

## Instruction Following

- Llama 3-8B: 58.7 (#255)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1214 |

## Long Context

- Llama 3-8B: 34.2 (#246)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1128 | 1246 |

## Writing & Preference

- Llama 3-8B: 37.7 (#251)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Llama 3-8B | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1166 | 1234 |
| LMArena Creative Writing | 1150 | 1195 |
| LMArena Multi-Turn | 1152 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Llama 3-8B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 30.9 to 25.3 on the Noometry Index.

### Which is cheaper, Llama 3-8B or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Llama 3-8B lists at $0.14 and $0.14.

### Is Llama 3-8B or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 30.5 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small 3 does, with 33K tokens against 8K.

### How many benchmarks do Llama 3-8B and Mistral Small 3 share?

22 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Mistral Small 3 has 24.