# Llama 2-70B vs Mistral Medium

> Mistral Medium is the stronger model overall, scoring 36.3 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-2-70b-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Mistral Medium in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 32.3.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 81.6% for Mistral Medium.

## Snapshot

| | Llama 2-70B | Mistral Medium |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 36.3 |
| Rank | 349 | 218 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- Llama 2-70B: 31.4 (#286)
- Mistral Medium: 34.2 (#243)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Coding | 1079 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| ALE-Bench | — | 763.98 |

## Agentic & Tool Use

- Llama 2-70B: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Llama 2-70B: 14.4 (#325)
- Mistral Medium: 24.0 (#167)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1426 |
| DTBench | 41.6% | 75.5% |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |

## Math

- Llama 2-70B: 8.1 (#326)
- Mistral Medium: 28.1 (#245)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 32.2% |
| LMArena Math | 1091 | 1408 |
| MATH Level 5 | 3.3% | 81.6% |
| ProofBench | — | 9% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 69.6% | — |

## Knowledge

- Llama 2-70B: 7.4 (#310)
- Mistral Medium: 25.0 (#265)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| GPQA Diamond | 26.3% | 59.5% |
| LMArena Expert | 1039 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |

## Multimodal

- Llama 2-70B: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Llama 2-70B: 27.7 (#274)
- Mistral Medium: 52.1 (#91)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1045 | 1408 |
| LMArena Chinese | 995 | 1447 |
| LMArena French | 1090 | 1459 |
| LMArena German | 1041 | 1432 |
| LMArena Japanese | 927 | 1378 |
| LMArena Korean | 964 | 1380 |
| LMArena Russian | 1083 | 1411 |
| LMArena Spanish | 1143 | 1433 |

## Instruction Following

- Llama 2-70B: 54.9 (#278)
- Mistral Medium: 73.7 (#116)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1071 | 1398 |

## Long Context

- Llama 2-70B: 32.3 (#270)
- Mistral Medium: 42.9 (#114)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1062 | 1406 |

## Writing & Preference

- Llama 2-70B: 32.3 (#279)
- Mistral Medium: 60.0 (#103)

| Benchmark | Llama 2-70B | Mistral Medium |
|---|---|---|
| LMArena Text | 1115 | 1424 |
| LMArena Creative Writing | 1075 | 1391 |
| LMArena Multi-Turn | 1088 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

### Is Llama 2-70B better than Mistral Medium?

Mistral Medium is the stronger model overall, scoring 36.3 to 24.4 on the Noometry Index.

### Is Llama 2-70B or Mistral Medium better for coding?

Mistral Medium scores higher on coding benchmarks: 34.2 versus 31.4 in the Noometry coding category.

### How many benchmarks do Llama 2-70B and Mistral Medium share?

21 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral Medium has 36.