# Llama 3-70B vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.0 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-70b-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Mistral Medium in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Medium leads 52.3 to 33.8.
- The biggest single-benchmark swing is MATH Level 5: 22.6% for Llama 3-70B and 81.6% for Mistral Medium.

## Snapshot

| | Llama 3-70B | Mistral Medium |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.5 | 36.0 |
| Rank | 317 | 211 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- Llama 3-70B: 35.3 (#215)
- Mistral Medium: 33.8 (#241)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1206 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |

## Agentic & Tool Use

- Llama 3-70B: 20.9 (#132)
- Mistral Medium: 28.1 (#84)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| Cybench | 5% | — |

## Reasoning

- Llama 3-70B: 17.4 (#284)
- Mistral Medium: 23.3 (#165)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 35.1% | 50% |
| LMArena Hard Prompts | 1195 | 1426 |
| DTBench | 54.2% | 75.5% |
| CritPt | — | 0% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 122.91 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |

## Math

- Llama 3-70B: 12.0 (#299)
- Mistral Medium: 27.2 (#238)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 32.2% |
| LMArena Math | 1218 | 1409 |
| MATH Level 5 | 22.6% | 81.6% |
| ProofBench | — | 9% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Llama 3-70B: 20.8 (#272)
- Mistral Medium: 24.9 (#260)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 40.6% | 59.5% |
| LMArena Expert | 1149 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| MMLU | 79.3% | — |

## Multimodal

- Llama 3-70B: —
- Mistral Medium: 34.6 (#82)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Llama 3-70B: 33.8 (#246)
- Mistral Medium: 52.3 (#86)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1142 | 1408 |
| LMArena Chinese | 1114 | 1448 |
| LMArena French | 1231 | 1460 |
| LMArena German | 1169 | 1433 |
| LMArena Japanese | 1017 | 1378 |
| LMArena Korean | 1017 | 1382 |
| LMArena Russian | 1159 | 1411 |
| LMArena Spanish | 1241 | 1433 |

## Instruction Following

- Llama 3-70B: 62.8 (#233)
- Mistral Medium: 73.9 (#111)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1194 | 1398 |

## Long Context

- Llama 3-70B: 35.6 (#235)
- Mistral Medium: 42.9 (#108)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1174 | 1406 |

## Writing & Preference

- Llama 3-70B: 43.0 (#225)
- Mistral Medium: 60.2 (#97)

| Benchmark | Llama 3-70B | Mistral Medium |
|---|---|---|
| LMArena Text | 1221 | 1424 |
| LMArena Creative Writing | 1210 | 1391 |
| LMArena Multi-Turn | 1223 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

### Is Llama 3-70B better than Mistral Medium?

Mistral Medium is the stronger model overall, scoring 36.0 to 28.5 on the Noometry Index.

### Is Llama 3-70B or Mistral Medium better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.3 versus 33.8 in the Noometry coding category.

### How many benchmarks do Llama 3-70B and Mistral Medium share?

22 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Mistral Medium has 36.