# Llama 3-70B vs Mistral Large

> Mistral Large is the stronger model overall, scoring 31.9 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-70b-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Llama 3-70B scores higher in 3 categories and Mistral Large in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.1 to 20.8.
- The biggest single-benchmark swing is MATH Level 5: 22.6% for Llama 3-70B and 50.3% for Mistral Large.

## Snapshot

| | Llama 3-70B | Mistral Large |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.8 | 31.9 |
| Rank | 323 | 263 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Llama 3-70B: 35.8 (#218)
- Mistral Large: 34.3 (#240)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 43.6% | 30% |
| LMArena Coding | 1206 | 1277 |
| BigCodeBench Complete | 54.5% | 38.3% |
| HumanEval+ | 72% | 62.2% |
| MBPP+ | 69% | 59.5% |
| SciCode | — | 36.2% |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | — | 264.7 |

## Agentic & Tool Use

- Llama 3-70B: 21.1 (#139)
- Mistral Large: 28.6 (#89)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| Cybench | 5% | — |

## Reasoning

- Llama 3-70B: 18.0 (#288)
- Mistral Large: 15.8 (#310)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1257 |
| DTBench | 54.2% | 65.1% |
| Epoch Capabilities Index | 122.93 | 128.52 |
| ForecastBench | 57.1 | 57.1 |
| SimpleBench | — | 22.5% |
| Kagi LLM Benchmark | 35.1% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| LiveBench | — | 48.4% |
| WinoGrande | 83.5% | — |

## Math

- Llama 3-70B: 12.8 (#305)
- Mistral Large: 18.2 (#291)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 8.5% |
| LMArena Math | 1218 | 1262 |
| MATH Level 5 | 22.6% | 50.3% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Llama 3-70B: 20.8 (#277)
- Mistral Large: 30.1 (#230)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| GPQA Diamond | 40.6% | 51.3% |
| LMArena Expert | 1149 | 1232 |
| MMLU | 79.3% | 80% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |

## Multilingual

- Llama 3-70B: 33.6 (#251)
- Mistral Large: 40.0 (#219)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1142 | 1237 |
| LMArena Chinese | 1114 | 1240 |
| LMArena French | 1232 | 1325 |
| LMArena German | 1169 | 1254 |
| LMArena Japanese | 1017 | 1188 |
| LMArena Korean | 1017 | 1202 |
| LMArena Russian | 1159 | 1257 |
| LMArena Spanish | 1241 | 1268 |

## Instruction Following

- Llama 3-70B: 62.5 (#238)
- Mistral Large: 67.9 (#191)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1194 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Llama 3-70B: 35.6 (#240)
- Mistral Large: 38.3 (#199)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1174 | 1261 |

## Writing & Preference

- Llama 3-70B: 42.8 (#231)
- Mistral Large: 40.7 (#242)

| Benchmark | Llama 3-70B | Mistral Large |
|---|---|---|
| LMArena Text | 1221 | 1266 |
| LMArena Creative Writing | 1210 | 1243 |
| LMArena Multi-Turn | 1223 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

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

Mistral Large is the stronger model overall, scoring 31.9 to 28.8 on the Noometry Index.

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

Llama 3-70B scores higher on coding benchmarks: 35.8 versus 34.3 in the Noometry coding category.

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

28 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Mistral Large has 51.