Model comparison
Llama 2-70B vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 24.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Mistral Large 3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 8.1.
Side by side
| Llama 2-70B | Mistral Large 3 | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 39.1 |
| Released | 2023-07-18 | 2025-12-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 35 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 3 leads
Llama 2-70B: 31.4 (#286), Mistral Large 3: 34.4 (#237)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1079 | 1448 |
| LMArena WebDev | — | 1230 |
Reasoning Too close to call
Llama 2-70B: 14.4 (#325), Mistral Large 3: 15.2 (#319)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| DTBench | 41.6% | — |
| 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 Mistral Large 3 leads
Llama 2-70B: 8.1 (#326), Mistral Large 3: 38.7 (#129)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1091 | 1414 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Mistral Large 3 leads
Llama 2-70B: 7.4 (#310), Mistral Large 3: 36.0 (#177)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1039 | 1421 |
| GPQA Diamond | 26.3% | — |
| Vectara Hallucination Rate | — | 14.5% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multimodal Not comparable
Llama 2-70B: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Llama 2-70B: 27.7 (#274), Mistral Large 3: 52.5 (#84)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1045 | 1413 |
| LMArena Chinese | 995 | 1447 |
| LMArena French | 1090 | 1455 |
| LMArena German | 1041 | 1437 |
| LMArena Japanese | 927 | 1394 |
| LMArena Korean | 964 | 1384 |
| LMArena Russian | 1083 | 1411 |
| LMArena Spanish | 1143 | 1440 |
Instruction Following Mistral Large 3 leads
Llama 2-70B: 54.9 (#278), Mistral Large 3: 74.0 (#108)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1071 | 1403 |
Long Context Mistral Large 3 leads
Llama 2-70B: 32.3 (#270), Mistral Large 3: 43.1 (#105)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1062 | 1413 |
Writing & Preference Mistral Large 3 leads
Llama 2-70B: 32.3 (#279), Mistral Large 3: 60.0 (#101)
| Benchmark | Llama 2-70B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1115 | 1428 |
| LMArena Creative Writing | 1075 | 1386 |
| LMArena Multi-Turn | 1088 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is Llama 2-70B better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 24.4 on the Noometry Index.
Is Llama 2-70B or Mistral Large 3 better for coding?
Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Mistral Large 3 share?
17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral Large 3 has 24.