# Llama 3.1-70B vs Mistral Large 3

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-70b-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.2 to 35.6.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
- Mistral Large 3 accepts more context: 262K tokens versus 128K.

## Snapshot

| | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.4 | 38.6 |
| Rank | 299 | 172 |
| Context | 128K | 262K |
| Input $/M | $0.40 | $0.25 |
| Output $/M | $0.40 | $0.75 |
| Weights | Open | Open |

## Coding

- Llama 3.1-70B: 29.8 (#292)
- Mistral Large 3: 34.1 (#230)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1260 | 1447 |
| LMArena WebDev | — | 1230 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |

## Agentic & Tool Use

- Llama 3.1-70B: 24.9 (#104)
- Mistral Large 3: —

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |

## Reasoning

- Llama 3.1-70B: 20.8 (#215)
- Mistral Large 3: 14.6 (#314)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.91 | — |

## Math

- Llama 3.1-70B: 12.7 (#298)
- Mistral Large 3: 36.0 (#131)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1252 | 1415 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |

## Knowledge

- Llama 3.1-70B: 24.1 (#264)
- Mistral Large 3: 35.5 (#173)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1209 | 1421 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| Vectara Hallucination Rate | — | 14.5% |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |

## Multimodal

- Llama 3.1-70B: —
- Mistral Large 3: 37.6 (#65)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Llama 3.1-70B: 38.9 (#220)
- Mistral Large 3: 52.6 (#79)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1219 | 1412 |
| LMArena Chinese | 1215 | 1448 |
| LMArena French | 1260 | 1456 |
| LMArena German | 1222 | 1438 |
| LMArena Japanese | 1132 | 1399 |
| LMArena Korean | 1140 | 1384 |
| LMArena Russian | 1234 | 1412 |
| LMArena Spanish | 1253 | 1437 |

## Instruction Following

- Llama 3.1-70B: 65.5 (#218)
- Mistral Large 3: 74.1 (#104)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1231 | 1402 |
| IFEval | 82.1% | — |

## Long Context

- Llama 3.1-70B: 37.6 (#208)
- Mistral Large 3: 43.1 (#102)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1241 | 1413 |

## Writing & Preference

- Llama 3.1-70B: 35.6 (#262)
- Mistral Large 3: 60.2 (#100)

| Benchmark | Llama 3.1-70B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1261 | 1427 |
| LMArena Creative Writing | 1232 | 1385 |
| EQ-Bench Creative Writing | 784 | 1412 |
| LMArena Multi-Turn | 1256 | 1429 |
| WildBench | 75.8% | — |

## FAQ

### Is Llama 3.1-70B better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 29.4 on the Noometry Index.

### Which is cheaper, Llama 3.1-70B or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.

### Is Llama 3.1-70B or Mistral Large 3 better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 29.8 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 128K.

### How many benchmarks do Llama 3.1-70B and Mistral Large 3 share?

18 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Mistral Large 3 has 24.